├── .gitignore ├── INSTALLATION.md ├── LICENSE ├── README.md ├── assets └── teaser.png ├── baselines ├── base.py ├── config.json ├── gemini │ ├── __init__.py │ ├── extract_frames.py │ └── upload.py ├── gemini_modeling.py ├── gpt4o │ ├── __init__.py │ └── api_wrap.py ├── gpt4o_modeling.py ├── gpt4v │ ├── __init__.py │ └── api_wrap.py ├── gpt4v_modeling.py ├── llamavid │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── model │ │ ├── __init__.py │ │ ├── builder.py │ │ ├── language_model │ │ │ └── llava_llama_vid.py │ │ ├── llamavid_arch.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ ├── clip_encoder.py │ │ │ └── eva_vit.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ └── qformer.py │ ├── processor │ │ ├── clip-patch14-224 │ │ │ ├── config.json │ │ │ └── preprocessor_config.json │ │ └── clip-patch14-336 │ │ │ ├── config.json │ │ │ └── preprocessor_config.json │ ├── serve │ │ ├── __init__.py │ │ ├── cli.py │ │ ├── controller.py │ │ ├── examples │ │ │ ├── Avatar.png │ │ │ ├── Avengers.jpg │ │ │ ├── Forrest_Gump.jpg │ │ │ ├── Interstellar.jpg │ │ │ ├── Titanic.jpg │ │ │ ├── extreme_ironing.jpg │ │ │ └── waterview.jpg │ │ ├── gradio_web_server.py │ │ ├── model_worker.py │ │ ├── model_worker_short.py │ │ ├── register_worker.py │ │ └── run_llamavid_movie.py │ └── train │ │ ├── llama_flash_attn_monkey_patch.py │ │ ├── llava_trainer.py │ │ ├── train.py │ │ └── train_mem.py ├── llamavid_modeling.py ├── llava │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── eval │ │ ├── eval_gpt_review.py │ │ ├── eval_gpt_review_bench.py │ │ ├── eval_gpt_review_visual.py │ │ ├── eval_pope.py │ │ ├── eval_science_qa.py │ │ ├── eval_science_qa_gpt4.py │ │ ├── eval_science_qa_gpt4_requery.py │ │ ├── eval_textvqa.py │ │ ├── generate_webpage_data_from_table.py │ │ ├── m4c_evaluator.py │ │ ├── model_qa.py │ │ ├── model_vqa.py │ │ ├── model_vqa_loader.py │ │ ├── model_vqa_mmbench.py │ │ ├── model_vqa_science.py │ │ ├── qa_baseline_gpt35.py │ │ ├── run_llava.py │ │ ├── summarize_gpt_review.py │ │ ├── table │ │ │ ├── answer │ │ │ │ ├── answer_alpaca-13b.jsonl │ │ │ │ ├── answer_bard.jsonl │ │ │ │ ├── answer_gpt35.jsonl │ │ │ │ ├── answer_llama-13b.jsonl │ │ │ │ └── answer_vicuna-13b.jsonl │ │ │ ├── caps_boxes_coco2014_val_80.jsonl │ │ │ ├── model.jsonl │ │ │ ├── prompt.jsonl │ │ │ ├── question.jsonl │ │ │ ├── results │ │ │ │ ├── test_sqa_llava_13b_v0.json │ │ │ │ └── test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json │ │ │ ├── review │ │ │ │ ├── review_alpaca-13b_vicuna-13b.jsonl │ │ │ │ ├── review_bard_vicuna-13b.jsonl │ │ │ │ ├── review_gpt35_vicuna-13b.jsonl │ │ │ │ └── review_llama-13b_vicuna-13b.jsonl │ │ │ ├── reviewer.jsonl │ │ │ └── rule.json │ │ └── webpage │ │ │ ├── figures │ │ │ ├── alpaca.png │ │ │ ├── bard.jpg │ │ │ ├── chatgpt.svg │ │ │ ├── llama.jpg │ │ │ ├── swords_FILL0_wght300_GRAD0_opsz48.svg │ │ │ └── vicuna.jpeg │ │ │ ├── index.html │ │ │ ├── script.js │ │ │ └── styles.css │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model │ │ │ ├── llava_llama.py │ │ │ ├── llava_mistral.py │ │ │ └── llava_mpt.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ └── clip_encoder.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ └── utils.py │ ├── serve │ │ ├── __init__.py │ │ ├── cli.py │ │ ├── controller.py │ │ ├── examples │ │ │ ├── extreme_ironing.jpg │ │ │ └── waterview.jpg │ │ ├── gradio_web_server.py │ │ ├── model_worker.py │ │ ├── register_worker.py │ │ ├── sglang_worker.py │ │ └── test_message.py │ ├── train │ │ ├── llama_flash_attn_monkey_patch.py │ │ ├── llama_xformers_attn_monkey_patch.py │ │ ├── llava_trainer.py │ │ ├── train.py │ │ ├── train_mem.py │ │ └── train_xformers.py │ └── utils.py ├── llava_modeling.py ├── llavanext_modeling.py ├── llavavid │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model │ │ │ ├── llava_llama.py │ │ │ ├── llava_mistral.py │ │ │ └── llava_mpt.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ └── clip_encoder.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ ├── multimodal_resampler │ │ │ ├── builder.py │ │ │ └── spatial_pool.py │ │ └── utils.py │ └── utils.py ├── minigpt4 │ ├── __init__.py │ ├── common │ │ ├── __init__.py │ │ ├── config.py │ │ ├── dist_utils.py │ │ ├── eval_utils.py │ │ ├── gradcam.py │ │ ├── logger.py │ │ ├── optims.py │ │ ├── registry.py │ │ ├── utils.py │ │ └── vqa_tools │ │ │ ├── VQA │ │ │ ├── PythonEvaluationTools │ │ │ │ ├── vqaEvalDemo.py │ │ │ │ └── vqaEvaluation │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── vqaEval.py │ │ │ ├── PythonHelperTools │ │ │ │ ├── vqaDemo.py │ │ │ │ └── vqaTools │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── vqa.py │ │ │ └── README.md │ │ │ ├── __init__.py │ │ │ ├── aokvqa │ │ │ ├── LICENSE │ │ │ ├── README.md │ │ │ ├── data_scripts │ │ │ │ ├── build_vocab.py │ │ │ │ ├── encode_vocab_clip.py │ │ │ │ ├── extract_bert_features.py │ │ │ │ ├── extract_clip_features.py │ │ │ │ └── extract_resnet_features.py │ │ │ ├── environment.yml │ │ │ ├── evaluation │ │ │ │ ├── eval_predictions.py │ │ │ │ ├── load_aokvqa.py │ │ │ │ ├── prepare_predictions.py │ │ │ │ └── remap_predictions.py │ │ │ ├── gpt3 │ │ │ │ ├── README.md │ │ │ │ ├── caption_inputs.py │ │ │ │ ├── query_gpt3.py │ │ │ │ └── rationale_inputs.py │ │ │ ├── heuristics │ │ │ │ ├── README.md │ │ │ │ ├── most_common_answer.py │ │ │ │ ├── random_unweighted.py │ │ │ │ └── random_weighted.py │ │ │ ├── load_aokvqa.py │ │ │ └── transfer_experiments │ │ │ │ ├── README.md │ │ │ │ ├── predict.py │ │ │ │ └── train.py │ │ │ ├── vqa.py │ │ │ └── vqa_eval.py │ ├── configs │ │ ├── datasets │ │ │ ├── cc_sbu │ │ │ │ ├── align.yaml │ │ │ │ └── defaults.yaml │ │ │ ├── cmd_video │ │ │ │ └── default.yaml │ │ │ ├── laion │ │ │ │ └── defaults.yaml │ │ │ ├── template │ │ │ │ └── default.yaml │ │ │ ├── video_chatgpt │ │ │ │ └── default.yaml │ │ │ └── webvid │ │ │ │ └── default.yaml │ │ ├── default.yaml │ │ └── models │ │ │ ├── minigpt4.yaml │ │ │ └── minigpt4v.yaml │ ├── conversation │ │ ├── __init__.py │ │ └── conversation.py │ ├── datasets │ │ ├── __init__.py │ │ ├── builders │ │ │ ├── __init__.py │ │ │ ├── base_dataset_builder.py │ │ │ ├── image_text_pair_builder.py │ │ │ └── vqa_builder.py │ │ ├── data_utils.py │ │ └── datasets │ │ │ ├── __init__.py │ │ │ ├── aok_vqa_datasets.py │ │ │ ├── aok_vqa_reasoning_datasets.py │ │ │ ├── base_dataset.py │ │ │ ├── caption_datasets.py │ │ │ ├── caption_reasoning.py │ │ │ ├── cc_sbu_dataset.py │ │ │ ├── coco_caption.py │ │ │ ├── coco_vqa_datasets.py │ │ │ ├── cot.py │ │ │ ├── coyo_dataset.py │ │ │ ├── dataloader_utils.py │ │ │ ├── doc_dataset.py │ │ │ ├── gqa_datasets.py │ │ │ ├── grounded_caption_reasoning.py │ │ │ ├── grounded_detailed_image_caption_dataset.py │ │ │ ├── laion_dataset.py │ │ │ ├── llava_dataset.py │ │ │ ├── locna_dataset.py │ │ │ ├── lvis_dataset.py │ │ │ ├── nav_dataset.py │ │ │ ├── open_images.py │ │ │ ├── paint_dataset.py │ │ │ ├── reasoning_dataset.py │ │ │ ├── text_caps.py │ │ │ ├── textvqa_datasets.py │ │ │ ├── unnatural_instruction.py │ │ │ ├── vg_dataset.py │ │ │ ├── video_datasets.py │ │ │ └── vqa_datasets.py │ ├── mistral_test_config.yaml │ ├── models │ │ ├── Qformer.py │ │ ├── __init__.py │ │ ├── base_model.py │ │ ├── blip2.py │ │ ├── blip2_outputs.py │ │ ├── clip_vision_encoder.py │ │ ├── eva_vit.py │ │ ├── mini_gpt4_llama_v2.py │ │ ├── mistral.py │ │ ├── modeling_llama_v2.py │ │ ├── modeling_mistral.py │ │ └── policies │ │ │ ├── __init__.py │ │ │ ├── activation_checkpointing_functions.py │ │ │ ├── anyprecision_optimizer.py │ │ │ ├── fsdp_utils.py │ │ │ ├── mixed_precision.py │ │ │ └── wrapping.py │ ├── processors │ │ ├── __init__.py │ │ ├── base_processor.py │ │ ├── blip_processors.py │ │ └── randaugment.py │ ├── runners │ │ ├── __init__.py │ │ └── runner_base.py │ └── tasks │ │ ├── __init__.py │ │ ├── base_task.py │ │ ├── image_text_pretrain.py │ │ ├── vqa.py │ │ └── vqa_reading_comprehension.py ├── minigpt4video_modeling.py ├── pllava │ ├── models │ │ ├── __init__.py │ │ └── pllava │ │ │ ├── __init__.py │ │ │ ├── configuration_pllava.py │ │ │ ├── convert_pllava_weights_to_hf.py │ │ │ ├── modeling_pllava.py │ │ │ └── processing_pllava.py │ ├── tasks │ │ ├── eval │ │ │ ├── demo │ │ │ │ ├── __init__.py │ │ │ │ ├── pllava_demo.py │ │ │ │ ├── show_compare.py │ │ │ │ └── show_gallery.py │ │ │ ├── eval_utils.py │ │ │ ├── model_utils.py │ │ │ ├── mvbench │ │ │ │ ├── __init__.py │ │ │ │ └── pllava_eval_mvbench.py │ │ │ ├── recaption │ │ │ │ ├── __init__.py │ │ │ │ ├── pllava_recaption.py │ │ │ │ └── show_recaption.py │ │ │ ├── vcgbench │ │ │ │ ├── __init__.py │ │ │ │ ├── pllava_eval_vcgbench.py │ │ │ │ └── show_vcg.py │ │ │ └── videoqabench │ │ │ │ ├── __init__.py │ │ │ │ └── pllava_eval_videoqabench.py │ │ ├── shared_utils.py │ │ └── train │ │ │ ├── config_pllava_nframe.py │ │ │ ├── config_pllava_nframe_yiprompt.py │ │ │ ├── instruction_data.py │ │ │ └── train_pllava_nframe_accel.py │ └── utils │ │ ├── basic_utils.py │ │ ├── config.py │ │ ├── config_utils.py │ │ ├── distributed.py │ │ ├── easydict.py │ │ ├── logger.py │ │ ├── optimizer.py │ │ └── scheduler.py ├── pllava_modeling.py ├── share4video │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── eval │ │ ├── evaluate_benchmark_1_correctness.py │ │ ├── evaluate_benchmark_2_detailed_orientation.py │ │ ├── evaluate_benchmark_3_context.py │ │ ├── evaluate_benchmark_4_temporal.py │ │ ├── evaluate_benchmark_5_consistency.py │ │ ├── model_vqa_loader.py │ │ ├── model_vqa_tempcompass.py │ │ ├── run_llava.py │ │ └── video │ │ │ ├── eval_mvbench.py │ │ │ ├── eval_vbench.py │ │ │ ├── general_utils.py │ │ │ ├── mvbench_utils.py │ │ │ └── vbench_utils.py │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model │ │ │ ├── llava_llama.py │ │ │ ├── llava_mistral.py │ │ │ └── llava_mpt.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ ├── clip_encoder.py │ │ │ └── siglip_encoder.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ └── utils.py │ ├── serve │ │ └── gradio_utils.py │ ├── train │ │ ├── llava_trainer.py │ │ ├── train.py │ │ └── train_mem.py │ ├── utils.py │ └── video_utils.py ├── sharegpt4video_modeling.py ├── valley │ ├── configs │ │ ├── deepspeed │ │ │ ├── config_zero2.json │ │ │ ├── config_zero3.json │ │ │ └── config_zero3_offload.json │ │ └── experiment │ │ │ ├── valley_stage1.yaml │ │ │ ├── valley_stage2.yaml │ │ │ ├── valley_stage2_lora.yaml │ │ │ └── valley_stage2_zero3.yaml │ ├── constants.py │ ├── conversation.py │ ├── data │ │ ├── dataset.py │ │ └── video_transform.py │ ├── inference │ │ ├── run_valley.py │ │ ├── run_valley_conv.py │ │ └── run_valley_llamma_v2.py │ ├── model │ │ ├── apply_delta.py │ │ ├── make_delta.py │ │ └── valley_model.py │ ├── train │ │ ├── train.py │ │ ├── train.sh │ │ └── trainner.py │ ├── util │ │ ├── config.py │ │ ├── data_util.py │ │ └── decode_img.py │ └── utils.py ├── valley_modeling.py ├── video_chat2 │ ├── configs │ │ ├── config.json │ │ ├── config_bert.json │ │ ├── data.py │ │ ├── instruction_data.py │ │ └── model.py │ ├── conversation.py │ ├── dataset │ │ ├── __init__.py │ │ ├── base_dataset.py │ │ ├── dataloader.py │ │ ├── it_dataset.py │ │ ├── pt_dataset.py │ │ ├── utils.py │ │ ├── video_transforms.py │ │ └── video_utils.py │ ├── models │ │ ├── __init__.py │ │ ├── bert │ │ │ ├── __init__.py │ │ │ ├── builder.py │ │ │ ├── tokenization_bert.py │ │ │ └── xbert.py │ │ ├── blip2 │ │ │ ├── Qformer.py │ │ │ ├── __init__.py │ │ │ ├── blip2.py │ │ │ ├── builder.py │ │ │ ├── modeling_llama.py │ │ │ ├── modeling_llama_mem.py │ │ │ ├── utils.py │ │ │ └── vit.py │ │ ├── criterions.py │ │ ├── utils.py │ │ ├── videochat2_it.py │ │ ├── videochat2_pt.py │ │ └── videochat2_qformer.py │ ├── prompts │ │ ├── concise_description.txt │ │ └── concise_image_description.txt │ ├── tasks │ │ ├── retrieval_utils.py │ │ ├── shared_utils.py │ │ ├── shared_utils_qformer.py │ │ ├── train_it.py │ │ ├── train_pt.py │ │ └── train_qformer.py │ └── utils │ │ ├── basic_utils.py │ │ ├── config.py │ │ ├── config_utils.py │ │ ├── distributed.py │ │ ├── easydict.py │ │ ├── logger.py │ │ ├── optimizer.py │ │ └── scheduler.py ├── video_chatgpt │ ├── __init__.py │ ├── constants.py │ ├── demo │ │ ├── __init__.py │ │ ├── chat.py │ │ ├── gradio_css.py │ │ ├── gradio_patch.py │ │ ├── template.py │ │ └── video_demo.py │ ├── eval │ │ ├── __init__.py │ │ ├── model_utils.py │ │ ├── run_inference_activitynet_qa.py │ │ ├── run_inference_benchmark_consistency.py │ │ └── run_inference_benchmark_general.py │ ├── inference.py │ ├── model │ │ ├── __init__.py │ │ ├── consolidate.py │ │ ├── make_delta.py │ │ ├── utils.py │ │ └── video_chatgpt.py │ ├── single_video_inference.py │ ├── train │ │ ├── llama_flash_attn_monkey_patch.py │ │ ├── llava_trainer.py │ │ ├── train.py │ │ └── train_mem.py │ ├── utils.py │ └── video_conversation.py ├── video_llama │ ├── __init__.py │ ├── common │ │ ├── __init__.py │ │ ├── config.py │ │ ├── dist_utils.py │ │ ├── gradcam.py │ │ ├── logger.py │ │ ├── optims.py │ │ ├── registry.py │ │ └── utils.py │ ├── configs │ │ ├── datasets │ │ │ ├── cc_sbu │ │ │ │ ├── align.yaml │ │ │ │ └── defaults.yaml │ │ │ ├── instruct │ │ │ │ ├── llava_instruct.yaml │ │ │ │ └── webvid_instruct.yaml │ │ │ ├── laion │ │ │ │ └── defaults.yaml │ │ │ └── webvid │ │ │ │ └── defaults.yaml │ │ ├── default.yaml │ │ └── models │ │ │ ├── minigpt4.yaml │ │ │ └── video_llama.yaml │ ├── conversation │ │ ├── __init__.py │ │ └── conversation_video.py │ ├── datasets │ │ ├── __init__.py │ │ ├── builders │ │ │ ├── __init__.py │ │ │ ├── base_dataset_builder.py │ │ │ ├── image_text_pair_builder.py │ │ │ ├── instruct_builder.py │ │ │ └── video_caption_builder.py │ │ ├── data_utils.py │ │ └── datasets │ │ │ ├── __init__.py │ │ │ ├── base_dataset.py │ │ │ ├── caption_datasets.py │ │ │ ├── cc_sbu_dataset.py │ │ │ ├── dataloader_utils.py │ │ │ ├── laion_dataset.py │ │ │ ├── llava_instruct_dataset.py │ │ │ ├── video_instruct_dataset.py │ │ │ └── webvid_datasets.py │ ├── models │ │ ├── ImageBind │ │ │ ├── .assets │ │ │ │ ├── bird_audio.wav │ │ │ │ ├── bird_image.jpg │ │ │ │ ├── car_audio.wav │ │ │ │ ├── car_image.jpg │ │ │ │ ├── dog_audio.wav │ │ │ │ └── dog_image.jpg │ │ │ ├── CODE_OF_CONDUCT.md │ │ │ ├── CONTRIBUTING.md │ │ │ ├── LICENSE │ │ │ ├── README.md │ │ │ ├── bpe │ │ │ │ └── bpe_simple_vocab_16e6.txt.gz │ │ │ ├── data.py │ │ │ ├── model_card.md │ │ │ ├── models │ │ │ │ ├── __init__.py │ │ │ │ ├── helpers.py │ │ │ │ ├── imagebind_model.py │ │ │ │ ├── multimodal_preprocessors.py │ │ │ │ └── transformer.py │ │ │ └── requirements.txt │ │ ├── Qformer.py │ │ ├── __init__.py │ │ ├── base_model.py │ │ ├── blip2.py │ │ ├── blip2_outputs.py │ │ ├── eva_vit.py │ │ ├── modeling_llama.py │ │ └── video_llama.py │ ├── processors │ │ ├── __init__.py │ │ ├── base_processor.py │ │ ├── blip_processors.py │ │ ├── functional_video.py │ │ ├── randaugment.py │ │ ├── transforms_video.py │ │ └── video_processor.py │ ├── runners │ │ ├── __init__.py │ │ ├── runner_base.py │ │ └── test.py │ ├── tasks │ │ ├── __init__.py │ │ ├── base_task.py │ │ ├── image_text_pretrain.py │ │ └── video_text_pretrain.py │ └── video_llama_eval_withaudio.yaml ├── videochat_modeling.py ├── videochatgpt_modeling.py ├── videolavit │ ├── __init__.py │ ├── conversation.py │ ├── models │ │ ├── __init__.py │ │ ├── modeling_3d_unet.py │ │ ├── modeling_decoder.py │ │ ├── modeling_motion_condition.py │ │ ├── modeling_motion_tokenizer.py │ │ ├── modeling_transformer_temporal.py │ │ ├── modeling_unet_3d_blocks.py │ │ ├── modeling_video_lavit_hf.py │ │ ├── modeling_visual_encoder.py │ │ ├── modeling_visual_tokenzier.py │ │ ├── transform.py │ │ ├── video_detokenizer.py │ │ ├── video_lavit_for_generation.py │ │ └── video_lavit_for_understanding.py │ └── utils.py ├── videolavit_modeling.py ├── videollama2 │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── eval │ │ ├── eval_audio_TUT2017.py │ │ ├── eval_audio_clotho.py │ │ ├── eval_audio_clothoAQA.py │ │ ├── eval_audio_video_AVQA.py │ │ ├── eval_audio_video_AVSD.py │ │ ├── eval_audio_video_AVSSD.py │ │ ├── eval_audio_vocalsound.py │ │ ├── eval_video_cap_msvc_correctness.py │ │ ├── eval_video_cap_msvc_detailedness.py │ │ ├── eval_video_mcqa_mvbench.py │ │ ├── eval_video_mcqa_videomme.py │ │ ├── eval_video_oqa_activitynet.py │ │ ├── eval_video_oqa_vcgpt_1_correctness.py │ │ ├── eval_video_oqa_vcgpt_2_detailed_orientation.py │ │ ├── eval_video_oqa_vcgpt_3_context.py │ │ ├── eval_video_oqa_vcgpt_4_temporal.py │ │ ├── eval_video_oqa_vcgpt_5_consistency.py │ │ ├── inference_audio.py │ │ ├── inference_audio_video.py │ │ ├── inference_video_cap_msvc.py │ │ ├── inference_video_mcqa_egoschema.py │ │ ├── inference_video_mcqa_mvbench.py │ │ ├── inference_video_mcqa_perception_test_mcqa.py │ │ ├── inference_video_mcqa_videomme.py │ │ ├── inference_video_oqa_activitynet.py │ │ ├── inference_video_oqa_vcgpt_consistency.py │ │ └── inference_video_oqa_vcgpt_general.py │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── beats │ │ │ ├── BEATs.py │ │ │ ├── LICENSE_beats │ │ │ ├── Tokenizers.py │ │ │ ├── __init__.py │ │ │ ├── backbone.py │ │ │ ├── modules.py │ │ │ ├── quantizer.py │ │ │ └── weight_norm_fix.py │ │ ├── encoder.py │ │ ├── mel_filters.npz │ │ ├── projector.py │ │ ├── videollama2_arch.py │ │ ├── videollama2_gemma2.py │ │ ├── videollama2_llama.py │ │ ├── videollama2_mistral.py │ │ ├── videollama2_mixtral.py │ │ ├── videollama2_phi3.py │ │ └── videollama2_qwen2.py │ ├── serve │ │ ├── cli.py │ │ ├── controller.py │ │ ├── examples │ │ │ ├── bird-twitter-car.wav │ │ │ ├── desert.jpg │ │ │ ├── door.of.bar.raining2.wav │ │ │ ├── extreme_ironing.jpg │ │ │ └── waterview.jpg │ │ ├── gradio_web_server.py │ │ ├── gradio_web_server_adhoc.py │ │ ├── gradio_web_server_adhoc_av.py │ │ ├── model_worker.py │ │ ├── register_worker.py │ │ ├── sglang_worker.py │ │ └── test_message.py │ ├── train.py │ ├── utils.py │ └── videollama2_trainer.py ├── videollama2_modeling.py ├── videollama_modeling.py ├── videollava │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model │ │ │ ├── llava_llama.py │ │ │ ├── llava_mpt.py │ │ │ └── mpt │ │ │ │ ├── adapt_tokenizer.py │ │ │ │ ├── attention.py │ │ │ │ ├── blocks.py │ │ │ │ ├── configuration_mpt.py │ │ │ │ ├── custom_embedding.py │ │ │ │ ├── flash_attn_triton.py │ │ │ │ ├── hf_prefixlm_converter.py │ │ │ │ ├── meta_init_context.py │ │ │ │ ├── modeling_mpt.py │ │ │ │ ├── norm.py │ │ │ │ └── param_init_fns.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ ├── clip_encoder.py │ │ │ └── languagebind │ │ │ │ ├── __init__.py │ │ │ │ ├── audio │ │ │ │ ├── configuration_audio.py │ │ │ │ ├── modeling_audio.py │ │ │ │ ├── processing_audio.py │ │ │ │ └── tokenization_audio.py │ │ │ │ ├── depth │ │ │ │ ├── configuration_depth.py │ │ │ │ ├── modeling_depth.py │ │ │ │ ├── processing_depth.py │ │ │ │ └── tokenization_depth.py │ │ │ │ ├── image │ │ │ │ ├── configuration_image.py │ │ │ │ ├── modeling_image.py │ │ │ │ ├── processing_image.py │ │ │ │ └── tokenization_image.py │ │ │ │ ├── thermal │ │ │ │ ├── configuration_thermal.py │ │ │ │ ├── modeling_thermal.py │ │ │ │ ├── processing_thermal.py │ │ │ │ └── tokenization_thermal.py │ │ │ │ └── video │ │ │ │ ├── configuration_video.py │ │ │ │ ├── modeling_video.py │ │ │ │ ├── processing_video.py │ │ │ │ └── tokenization_video.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ └── utils.py │ └── utils.py └── videollava_modeling.py ├── evaluations ├── evaluation.py ├── evaluation_bias.py ├── evaluation_bias_sep.py ├── evaluation_halluc.py ├── evaluation_pep.py ├── evaluation_pep_utils.py └── evaluation_utils.py ├── model_testing_zoo.py └── videohallucer_datasets ├── external_factual └── external_factual.json ├── external_nonfactual └── external_nonfactual.json ├── fact_detect ├── fact_detect.json ├── fact_detect_yn.json └── modify.py ├── interaction ├── conflict.jsonl ├── interaction.json └── stat.py ├── object_relation └── object_relation.json ├── semantic_detail └── semantic_detail.json └── temporal └── temporal.json /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/.gitignore -------------------------------------------------------------------------------- /INSTALLATION.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/INSTALLATION.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/README.md -------------------------------------------------------------------------------- /assets/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/assets/teaser.png -------------------------------------------------------------------------------- /baselines/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/base.py -------------------------------------------------------------------------------- /baselines/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/config.json -------------------------------------------------------------------------------- /baselines/gemini/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/gemini/extract_frames.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gemini/extract_frames.py -------------------------------------------------------------------------------- /baselines/gemini/upload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gemini/upload.py -------------------------------------------------------------------------------- /baselines/gemini_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gemini_modeling.py -------------------------------------------------------------------------------- /baselines/gpt4o/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/gpt4o/api_wrap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gpt4o/api_wrap.py -------------------------------------------------------------------------------- /baselines/gpt4o_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gpt4o_modeling.py -------------------------------------------------------------------------------- /baselines/gpt4v/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/gpt4v/api_wrap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gpt4v/api_wrap.py -------------------------------------------------------------------------------- /baselines/gpt4v_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/gpt4v_modeling.py -------------------------------------------------------------------------------- /baselines/llamavid/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import LlavaLlamaAttForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/llamavid/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/constants.py -------------------------------------------------------------------------------- /baselines/llamavid/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/conversation.py -------------------------------------------------------------------------------- /baselines/llamavid/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/__init__.py -------------------------------------------------------------------------------- /baselines/llamavid/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/builder.py -------------------------------------------------------------------------------- /baselines/llamavid/model/language_model/llava_llama_vid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/language_model/llava_llama_vid.py -------------------------------------------------------------------------------- /baselines/llamavid/model/llamavid_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/llamavid_arch.py -------------------------------------------------------------------------------- /baselines/llamavid/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /baselines/llamavid/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /baselines/llamavid/model/multimodal_encoder/eva_vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/multimodal_encoder/eva_vit.py -------------------------------------------------------------------------------- /baselines/llamavid/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /baselines/llamavid/model/qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/model/qformer.py -------------------------------------------------------------------------------- /baselines/llamavid/processor/clip-patch14-224/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/processor/clip-patch14-224/config.json -------------------------------------------------------------------------------- /baselines/llamavid/processor/clip-patch14-224/preprocessor_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/processor/clip-patch14-224/preprocessor_config.json -------------------------------------------------------------------------------- /baselines/llamavid/processor/clip-patch14-336/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/processor/clip-patch14-336/config.json -------------------------------------------------------------------------------- /baselines/llamavid/processor/clip-patch14-336/preprocessor_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/processor/clip-patch14-336/preprocessor_config.json -------------------------------------------------------------------------------- /baselines/llamavid/serve/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/llamavid/serve/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/cli.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/controller.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/Avatar.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/Avatar.png -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/Avengers.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/Avengers.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/Forrest_Gump.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/Forrest_Gump.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/Interstellar.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/Interstellar.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/Titanic.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/Titanic.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/extreme_ironing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/extreme_ironing.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/examples/waterview.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/examples/waterview.jpg -------------------------------------------------------------------------------- /baselines/llamavid/serve/gradio_web_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/gradio_web_server.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/model_worker.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/model_worker_short.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/model_worker_short.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/register_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/register_worker.py -------------------------------------------------------------------------------- /baselines/llamavid/serve/run_llamavid_movie.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/serve/run_llamavid_movie.py -------------------------------------------------------------------------------- /baselines/llamavid/train/llama_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/train/llama_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /baselines/llamavid/train/llava_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/train/llava_trainer.py -------------------------------------------------------------------------------- /baselines/llamavid/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/train/train.py -------------------------------------------------------------------------------- /baselines/llamavid/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid/train/train_mem.py -------------------------------------------------------------------------------- /baselines/llamavid_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llamavid_modeling.py -------------------------------------------------------------------------------- /baselines/llava/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import LlavaLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/llava/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/constants.py -------------------------------------------------------------------------------- /baselines/llava/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/conversation.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_gpt_review.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_gpt_review_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_gpt_review_bench.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_gpt_review_visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_gpt_review_visual.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_pope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_pope.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_science_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_science_qa.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_science_qa_gpt4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_science_qa_gpt4.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_science_qa_gpt4_requery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_science_qa_gpt4_requery.py -------------------------------------------------------------------------------- /baselines/llava/eval/eval_textvqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/eval_textvqa.py -------------------------------------------------------------------------------- /baselines/llava/eval/generate_webpage_data_from_table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/generate_webpage_data_from_table.py -------------------------------------------------------------------------------- /baselines/llava/eval/m4c_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/m4c_evaluator.py -------------------------------------------------------------------------------- /baselines/llava/eval/model_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/model_qa.py -------------------------------------------------------------------------------- /baselines/llava/eval/model_vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/model_vqa.py -------------------------------------------------------------------------------- /baselines/llava/eval/model_vqa_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/model_vqa_loader.py -------------------------------------------------------------------------------- /baselines/llava/eval/model_vqa_mmbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/model_vqa_mmbench.py -------------------------------------------------------------------------------- /baselines/llava/eval/model_vqa_science.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/model_vqa_science.py -------------------------------------------------------------------------------- /baselines/llava/eval/qa_baseline_gpt35.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/qa_baseline_gpt35.py -------------------------------------------------------------------------------- /baselines/llava/eval/run_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/run_llava.py -------------------------------------------------------------------------------- /baselines/llava/eval/summarize_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/summarize_gpt_review.py -------------------------------------------------------------------------------- /baselines/llava/eval/table/answer/answer_alpaca-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/answer/answer_alpaca-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/answer/answer_bard.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/answer/answer_bard.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/answer/answer_gpt35.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/answer/answer_gpt35.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/answer/answer_llama-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/answer/answer_llama-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/answer/answer_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/answer/answer_vicuna-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/caps_boxes_coco2014_val_80.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/caps_boxes_coco2014_val_80.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/model.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/model.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/prompt.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/prompt.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/question.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/question.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/results/test_sqa_llava_13b_v0.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/results/test_sqa_llava_13b_v0.json -------------------------------------------------------------------------------- /baselines/llava/eval/table/results/test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/results/test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json -------------------------------------------------------------------------------- /baselines/llava/eval/table/review/review_alpaca-13b_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/review/review_alpaca-13b_vicuna-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/review/review_bard_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/review/review_bard_vicuna-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/review/review_gpt35_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/review/review_gpt35_vicuna-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/review/review_llama-13b_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/review/review_llama-13b_vicuna-13b.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/reviewer.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/reviewer.jsonl -------------------------------------------------------------------------------- /baselines/llava/eval/table/rule.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/table/rule.json -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/alpaca.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/alpaca.png -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/bard.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/bard.jpg -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/chatgpt.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/chatgpt.svg -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/llama.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/llama.jpg -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/swords_FILL0_wght300_GRAD0_opsz48.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/swords_FILL0_wght300_GRAD0_opsz48.svg -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/figures/vicuna.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/figures/vicuna.jpeg -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/index.html -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/script.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/script.js -------------------------------------------------------------------------------- /baselines/llava/eval/webpage/styles.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/eval/webpage/styles.css -------------------------------------------------------------------------------- /baselines/llava/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/mm_utils.py -------------------------------------------------------------------------------- /baselines/llava/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/__init__.py -------------------------------------------------------------------------------- /baselines/llava/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/apply_delta.py -------------------------------------------------------------------------------- /baselines/llava/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/builder.py -------------------------------------------------------------------------------- /baselines/llava/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/consolidate.py -------------------------------------------------------------------------------- /baselines/llava/model/language_model/llava_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/language_model/llava_llama.py -------------------------------------------------------------------------------- /baselines/llava/model/language_model/llava_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/language_model/llava_mistral.py -------------------------------------------------------------------------------- /baselines/llava/model/language_model/llava_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/language_model/llava_mpt.py -------------------------------------------------------------------------------- /baselines/llava/model/llava_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/llava_arch.py -------------------------------------------------------------------------------- /baselines/llava/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/make_delta.py -------------------------------------------------------------------------------- /baselines/llava/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /baselines/llava/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /baselines/llava/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /baselines/llava/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/model/utils.py -------------------------------------------------------------------------------- /baselines/llava/serve/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/llava/serve/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/cli.py -------------------------------------------------------------------------------- /baselines/llava/serve/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/controller.py -------------------------------------------------------------------------------- /baselines/llava/serve/examples/extreme_ironing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/examples/extreme_ironing.jpg -------------------------------------------------------------------------------- /baselines/llava/serve/examples/waterview.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/examples/waterview.jpg -------------------------------------------------------------------------------- /baselines/llava/serve/gradio_web_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/gradio_web_server.py -------------------------------------------------------------------------------- /baselines/llava/serve/model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/model_worker.py -------------------------------------------------------------------------------- /baselines/llava/serve/register_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/register_worker.py -------------------------------------------------------------------------------- /baselines/llava/serve/sglang_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/sglang_worker.py -------------------------------------------------------------------------------- /baselines/llava/serve/test_message.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/serve/test_message.py -------------------------------------------------------------------------------- /baselines/llava/train/llama_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/llama_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /baselines/llava/train/llama_xformers_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/llama_xformers_attn_monkey_patch.py -------------------------------------------------------------------------------- /baselines/llava/train/llava_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/llava_trainer.py -------------------------------------------------------------------------------- /baselines/llava/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/train.py -------------------------------------------------------------------------------- /baselines/llava/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/train_mem.py -------------------------------------------------------------------------------- /baselines/llava/train/train_xformers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/train/train_xformers.py -------------------------------------------------------------------------------- /baselines/llava/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava/utils.py -------------------------------------------------------------------------------- /baselines/llava_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llava_modeling.py -------------------------------------------------------------------------------- /baselines/llavanext_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavanext_modeling.py -------------------------------------------------------------------------------- /baselines/llavavid/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import LlavaLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/llavavid/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/constants.py -------------------------------------------------------------------------------- /baselines/llavavid/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/conversation.py -------------------------------------------------------------------------------- /baselines/llavavid/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/mm_utils.py -------------------------------------------------------------------------------- /baselines/llavavid/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/__init__.py -------------------------------------------------------------------------------- /baselines/llavavid/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/apply_delta.py -------------------------------------------------------------------------------- /baselines/llavavid/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/builder.py -------------------------------------------------------------------------------- /baselines/llavavid/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/consolidate.py -------------------------------------------------------------------------------- /baselines/llavavid/model/language_model/llava_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/language_model/llava_llama.py -------------------------------------------------------------------------------- /baselines/llavavid/model/language_model/llava_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/language_model/llava_mistral.py -------------------------------------------------------------------------------- /baselines/llavavid/model/language_model/llava_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/language_model/llava_mpt.py -------------------------------------------------------------------------------- /baselines/llavavid/model/llava_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/llava_arch.py -------------------------------------------------------------------------------- /baselines/llavavid/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/make_delta.py -------------------------------------------------------------------------------- /baselines/llavavid/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /baselines/llavavid/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /baselines/llavavid/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /baselines/llavavid/model/multimodal_resampler/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/multimodal_resampler/builder.py -------------------------------------------------------------------------------- /baselines/llavavid/model/multimodal_resampler/spatial_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/multimodal_resampler/spatial_pool.py -------------------------------------------------------------------------------- /baselines/llavavid/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/model/utils.py -------------------------------------------------------------------------------- /baselines/llavavid/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/llavavid/utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/minigpt4/common/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/config.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/dist_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/dist_utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/eval_utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/gradcam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/gradcam.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/logger.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/optims.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/optims.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/registry.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonEvaluationTools/vqaEvalDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/VQA/PythonEvaluationTools/vqaEvalDemo.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonEvaluationTools/vqaEvaluation/__init__.py: -------------------------------------------------------------------------------- 1 | author='aagrawal' 2 | -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonEvaluationTools/vqaEvaluation/vqaEval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/VQA/PythonEvaluationTools/vqaEvaluation/vqaEval.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonHelperTools/vqaDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/VQA/PythonHelperTools/vqaDemo.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonHelperTools/vqaTools/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'aagrawal' 2 | -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/PythonHelperTools/vqaTools/vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/VQA/PythonHelperTools/vqaTools/vqa.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/VQA/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/VQA/README.md -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/LICENSE -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/README.md -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/build_vocab.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/build_vocab.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/encode_vocab_clip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/encode_vocab_clip.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_bert_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_bert_features.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_clip_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_clip_features.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_resnet_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/data_scripts/extract_resnet_features.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/environment.yml -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/eval_predictions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/eval_predictions.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/load_aokvqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/load_aokvqa.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/prepare_predictions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/prepare_predictions.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/remap_predictions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/evaluation/remap_predictions.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/README.md -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/caption_inputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/caption_inputs.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/query_gpt3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/query_gpt3.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/rationale_inputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/gpt3/rationale_inputs.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/README.md -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/most_common_answer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/most_common_answer.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/random_unweighted.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/random_unweighted.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/random_weighted.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/heuristics/random_weighted.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/load_aokvqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/load_aokvqa.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/README.md -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/predict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/predict.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/aokvqa/transfer_experiments/train.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/vqa.py -------------------------------------------------------------------------------- /baselines/minigpt4/common/vqa_tools/vqa_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/common/vqa_tools/vqa_eval.py -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/cc_sbu/align.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/cc_sbu/align.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/cc_sbu/defaults.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/cc_sbu/defaults.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/cmd_video/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/cmd_video/default.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/laion/defaults.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/laion/defaults.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/template/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/template/default.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/video_chatgpt/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/video_chatgpt/default.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/datasets/webvid/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/datasets/webvid/default.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/default.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/models/minigpt4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/models/minigpt4.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/configs/models/minigpt4v.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/configs/models/minigpt4v.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/conversation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/minigpt4/conversation/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/conversation/conversation.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/builders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/builders/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/builders/base_dataset_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/builders/base_dataset_builder.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/builders/image_text_pair_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/builders/image_text_pair_builder.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/builders/vqa_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/builders/vqa_builder.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/data_utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/aok_vqa_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/aok_vqa_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/aok_vqa_reasoning_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/aok_vqa_reasoning_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/base_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/base_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/caption_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/caption_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/caption_reasoning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/caption_reasoning.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/cc_sbu_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/cc_sbu_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/coco_caption.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/coco_caption.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/coco_vqa_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/coco_vqa_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/cot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/cot.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/coyo_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/coyo_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/dataloader_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/dataloader_utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/doc_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/doc_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/gqa_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/gqa_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/grounded_caption_reasoning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/grounded_caption_reasoning.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/grounded_detailed_image_caption_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/grounded_detailed_image_caption_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/laion_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/laion_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/llava_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/llava_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/locna_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/locna_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/lvis_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/lvis_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/nav_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/nav_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/open_images.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/open_images.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/paint_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/paint_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/reasoning_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/reasoning_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/text_caps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/text_caps.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/textvqa_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/textvqa_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/unnatural_instruction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/unnatural_instruction.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/vg_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/vg_dataset.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/video_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/video_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/datasets/datasets/vqa_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/datasets/datasets/vqa_datasets.py -------------------------------------------------------------------------------- /baselines/minigpt4/mistral_test_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/mistral_test_config.yaml -------------------------------------------------------------------------------- /baselines/minigpt4/models/Qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/Qformer.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/base_model.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/blip2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/blip2.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/blip2_outputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/blip2_outputs.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/clip_vision_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/clip_vision_encoder.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/eva_vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/eva_vit.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/mini_gpt4_llama_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/mini_gpt4_llama_v2.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/mistral.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/modeling_llama_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/modeling_llama_v2.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/modeling_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/modeling_mistral.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/activation_checkpointing_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/activation_checkpointing_functions.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/anyprecision_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/anyprecision_optimizer.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/fsdp_utils.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/mixed_precision.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/mixed_precision.py -------------------------------------------------------------------------------- /baselines/minigpt4/models/policies/wrapping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/models/policies/wrapping.py -------------------------------------------------------------------------------- /baselines/minigpt4/processors/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/processors/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/processors/base_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/processors/base_processor.py -------------------------------------------------------------------------------- /baselines/minigpt4/processors/blip_processors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/processors/blip_processors.py -------------------------------------------------------------------------------- /baselines/minigpt4/processors/randaugment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/processors/randaugment.py -------------------------------------------------------------------------------- /baselines/minigpt4/runners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/runners/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/runners/runner_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/runners/runner_base.py -------------------------------------------------------------------------------- /baselines/minigpt4/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/tasks/__init__.py -------------------------------------------------------------------------------- /baselines/minigpt4/tasks/base_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/tasks/base_task.py -------------------------------------------------------------------------------- /baselines/minigpt4/tasks/image_text_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/tasks/image_text_pretrain.py -------------------------------------------------------------------------------- /baselines/minigpt4/tasks/vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/tasks/vqa.py -------------------------------------------------------------------------------- /baselines/minigpt4/tasks/vqa_reading_comprehension.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4/tasks/vqa_reading_comprehension.py -------------------------------------------------------------------------------- /baselines/minigpt4video_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/minigpt4video_modeling.py -------------------------------------------------------------------------------- /baselines/pllava/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/pllava/models/pllava/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/models/pllava/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/models/pllava/configuration_pllava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/models/pllava/configuration_pllava.py -------------------------------------------------------------------------------- /baselines/pllava/models/pllava/convert_pllava_weights_to_hf.py: -------------------------------------------------------------------------------- 1 | # Not yet -------------------------------------------------------------------------------- /baselines/pllava/models/pllava/modeling_pllava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/models/pllava/modeling_pllava.py -------------------------------------------------------------------------------- /baselines/pllava/models/pllava/processing_pllava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/models/pllava/processing_pllava.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/demo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/demo/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/demo/pllava_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/demo/pllava_demo.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/demo/show_compare.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/demo/show_compare.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/demo/show_gallery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/demo/show_gallery.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/eval_utils.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/model_utils.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/mvbench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/mvbench/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/mvbench/pllava_eval_mvbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/mvbench/pllava_eval_mvbench.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/recaption/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/recaption/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/recaption/pllava_recaption.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/recaption/pllava_recaption.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/recaption/show_recaption.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/recaption/show_recaption.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/vcgbench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/vcgbench/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/vcgbench/pllava_eval_vcgbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/vcgbench/pllava_eval_vcgbench.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/vcgbench/show_vcg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/vcgbench/show_vcg.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/videoqabench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/videoqabench/__init__.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/eval/videoqabench/pllava_eval_videoqabench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/eval/videoqabench/pllava_eval_videoqabench.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/shared_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/shared_utils.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/train/config_pllava_nframe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/train/config_pllava_nframe.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/train/config_pllava_nframe_yiprompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/train/config_pllava_nframe_yiprompt.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/train/instruction_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/train/instruction_data.py -------------------------------------------------------------------------------- /baselines/pllava/tasks/train/train_pllava_nframe_accel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/tasks/train/train_pllava_nframe_accel.py -------------------------------------------------------------------------------- /baselines/pllava/utils/basic_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/basic_utils.py -------------------------------------------------------------------------------- /baselines/pllava/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/config.py -------------------------------------------------------------------------------- /baselines/pllava/utils/config_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/config_utils.py -------------------------------------------------------------------------------- /baselines/pllava/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/distributed.py -------------------------------------------------------------------------------- /baselines/pllava/utils/easydict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/easydict.py -------------------------------------------------------------------------------- /baselines/pllava/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/logger.py -------------------------------------------------------------------------------- /baselines/pllava/utils/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/optimizer.py -------------------------------------------------------------------------------- /baselines/pllava/utils/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava/utils/scheduler.py -------------------------------------------------------------------------------- /baselines/pllava_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/pllava_modeling.py -------------------------------------------------------------------------------- /baselines/share4video/__init__.py: -------------------------------------------------------------------------------- 1 | # from .model import LlavaLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/share4video/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/constants.py -------------------------------------------------------------------------------- /baselines/share4video/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/conversation.py -------------------------------------------------------------------------------- /baselines/share4video/eval/evaluate_benchmark_1_correctness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/evaluate_benchmark_1_correctness.py -------------------------------------------------------------------------------- /baselines/share4video/eval/evaluate_benchmark_2_detailed_orientation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/evaluate_benchmark_2_detailed_orientation.py -------------------------------------------------------------------------------- /baselines/share4video/eval/evaluate_benchmark_3_context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/evaluate_benchmark_3_context.py -------------------------------------------------------------------------------- /baselines/share4video/eval/evaluate_benchmark_4_temporal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/evaluate_benchmark_4_temporal.py -------------------------------------------------------------------------------- /baselines/share4video/eval/evaluate_benchmark_5_consistency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/evaluate_benchmark_5_consistency.py -------------------------------------------------------------------------------- /baselines/share4video/eval/model_vqa_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/model_vqa_loader.py -------------------------------------------------------------------------------- /baselines/share4video/eval/model_vqa_tempcompass.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/model_vqa_tempcompass.py -------------------------------------------------------------------------------- /baselines/share4video/eval/run_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/run_llava.py -------------------------------------------------------------------------------- /baselines/share4video/eval/video/eval_mvbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/video/eval_mvbench.py -------------------------------------------------------------------------------- /baselines/share4video/eval/video/eval_vbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/video/eval_vbench.py -------------------------------------------------------------------------------- /baselines/share4video/eval/video/general_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/video/general_utils.py -------------------------------------------------------------------------------- /baselines/share4video/eval/video/mvbench_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/video/mvbench_utils.py -------------------------------------------------------------------------------- /baselines/share4video/eval/video/vbench_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/eval/video/vbench_utils.py -------------------------------------------------------------------------------- /baselines/share4video/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/mm_utils.py -------------------------------------------------------------------------------- /baselines/share4video/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/__init__.py -------------------------------------------------------------------------------- /baselines/share4video/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/apply_delta.py -------------------------------------------------------------------------------- /baselines/share4video/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/builder.py -------------------------------------------------------------------------------- /baselines/share4video/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/consolidate.py -------------------------------------------------------------------------------- /baselines/share4video/model/language_model/llava_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/language_model/llava_llama.py -------------------------------------------------------------------------------- /baselines/share4video/model/language_model/llava_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/language_model/llava_mistral.py -------------------------------------------------------------------------------- /baselines/share4video/model/language_model/llava_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/language_model/llava_mpt.py -------------------------------------------------------------------------------- /baselines/share4video/model/llava_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/llava_arch.py -------------------------------------------------------------------------------- /baselines/share4video/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/make_delta.py -------------------------------------------------------------------------------- /baselines/share4video/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /baselines/share4video/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /baselines/share4video/model/multimodal_encoder/siglip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/multimodal_encoder/siglip_encoder.py -------------------------------------------------------------------------------- /baselines/share4video/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /baselines/share4video/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/model/utils.py -------------------------------------------------------------------------------- /baselines/share4video/serve/gradio_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/serve/gradio_utils.py -------------------------------------------------------------------------------- /baselines/share4video/train/llava_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/train/llava_trainer.py -------------------------------------------------------------------------------- /baselines/share4video/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/train/train.py -------------------------------------------------------------------------------- /baselines/share4video/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/train/train_mem.py -------------------------------------------------------------------------------- /baselines/share4video/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/utils.py -------------------------------------------------------------------------------- /baselines/share4video/video_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/share4video/video_utils.py -------------------------------------------------------------------------------- /baselines/sharegpt4video_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/sharegpt4video_modeling.py -------------------------------------------------------------------------------- /baselines/valley/configs/deepspeed/config_zero2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/deepspeed/config_zero2.json -------------------------------------------------------------------------------- /baselines/valley/configs/deepspeed/config_zero3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/deepspeed/config_zero3.json -------------------------------------------------------------------------------- /baselines/valley/configs/deepspeed/config_zero3_offload.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/deepspeed/config_zero3_offload.json -------------------------------------------------------------------------------- /baselines/valley/configs/experiment/valley_stage1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/experiment/valley_stage1.yaml -------------------------------------------------------------------------------- /baselines/valley/configs/experiment/valley_stage2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/experiment/valley_stage2.yaml -------------------------------------------------------------------------------- /baselines/valley/configs/experiment/valley_stage2_lora.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/experiment/valley_stage2_lora.yaml -------------------------------------------------------------------------------- /baselines/valley/configs/experiment/valley_stage2_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/configs/experiment/valley_stage2_zero3.yaml -------------------------------------------------------------------------------- /baselines/valley/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/constants.py -------------------------------------------------------------------------------- /baselines/valley/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/conversation.py -------------------------------------------------------------------------------- /baselines/valley/data/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/data/dataset.py -------------------------------------------------------------------------------- /baselines/valley/data/video_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/data/video_transform.py -------------------------------------------------------------------------------- /baselines/valley/inference/run_valley.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/inference/run_valley.py -------------------------------------------------------------------------------- /baselines/valley/inference/run_valley_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/inference/run_valley_conv.py -------------------------------------------------------------------------------- /baselines/valley/inference/run_valley_llamma_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/inference/run_valley_llamma_v2.py -------------------------------------------------------------------------------- /baselines/valley/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/model/apply_delta.py -------------------------------------------------------------------------------- /baselines/valley/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/model/make_delta.py -------------------------------------------------------------------------------- /baselines/valley/model/valley_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/model/valley_model.py -------------------------------------------------------------------------------- /baselines/valley/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/train/train.py -------------------------------------------------------------------------------- /baselines/valley/train/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/train/train.sh -------------------------------------------------------------------------------- /baselines/valley/train/trainner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/train/trainner.py -------------------------------------------------------------------------------- /baselines/valley/util/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/util/config.py -------------------------------------------------------------------------------- /baselines/valley/util/data_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/util/data_util.py -------------------------------------------------------------------------------- /baselines/valley/util/decode_img.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/util/decode_img.py -------------------------------------------------------------------------------- /baselines/valley/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley/utils.py -------------------------------------------------------------------------------- /baselines/valley_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/valley_modeling.py -------------------------------------------------------------------------------- /baselines/video_chat2/configs/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/configs/config.json -------------------------------------------------------------------------------- /baselines/video_chat2/configs/config_bert.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/configs/config_bert.json -------------------------------------------------------------------------------- /baselines/video_chat2/configs/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/configs/data.py -------------------------------------------------------------------------------- /baselines/video_chat2/configs/instruction_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/configs/instruction_data.py -------------------------------------------------------------------------------- /baselines/video_chat2/configs/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/configs/model.py -------------------------------------------------------------------------------- /baselines/video_chat2/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/conversation.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/__init__.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/base_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/base_dataset.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/dataloader.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/it_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/it_dataset.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/pt_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/pt_dataset.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/video_transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/video_transforms.py -------------------------------------------------------------------------------- /baselines/video_chat2/dataset/video_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/dataset/video_utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_chat2/models/bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_chat2/models/bert/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/bert/builder.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/bert/tokenization_bert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/bert/tokenization_bert.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/bert/xbert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/bert/xbert.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/Qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/Qformer.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/blip2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/blip2.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/builder.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/modeling_llama.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/modeling_llama_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/modeling_llama_mem.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/blip2/vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/blip2/vit.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/criterions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/criterions.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/videochat2_it.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/videochat2_it.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/videochat2_pt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/videochat2_pt.py -------------------------------------------------------------------------------- /baselines/video_chat2/models/videochat2_qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/models/videochat2_qformer.py -------------------------------------------------------------------------------- /baselines/video_chat2/prompts/concise_description.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/prompts/concise_description.txt -------------------------------------------------------------------------------- /baselines/video_chat2/prompts/concise_image_description.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/prompts/concise_image_description.txt -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/retrieval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/retrieval_utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/shared_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/shared_utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/shared_utils_qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/shared_utils_qformer.py -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/train_it.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/train_it.py -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/train_pt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/train_pt.py -------------------------------------------------------------------------------- /baselines/video_chat2/tasks/train_qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/tasks/train_qformer.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/basic_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/basic_utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/config.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/config_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/config_utils.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/distributed.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/easydict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/easydict.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/logger.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/optimizer.py -------------------------------------------------------------------------------- /baselines/video_chat2/utils/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chat2/utils/scheduler.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import VideoChatGPTLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/video_chatgpt/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/constants.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/demo/chat.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/gradio_css.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/demo/gradio_css.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/gradio_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/demo/gradio_patch.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/demo/template.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/demo/video_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/demo/video_demo.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_chatgpt/eval/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/eval/model_utils.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/eval/run_inference_activitynet_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/eval/run_inference_activitynet_qa.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/eval/run_inference_benchmark_consistency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/eval/run_inference_benchmark_consistency.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/eval/run_inference_benchmark_general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/eval/run_inference_benchmark_general.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/inference.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/model/__init__.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/model/consolidate.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/model/make_delta.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/model/utils.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/model/video_chatgpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/model/video_chatgpt.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/single_video_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/single_video_inference.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/train/llama_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/train/llama_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/train/llava_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/train/llava_trainer.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/train/train.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/train/train_mem.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/utils.py -------------------------------------------------------------------------------- /baselines/video_chatgpt/video_conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_chatgpt/video_conversation.py -------------------------------------------------------------------------------- /baselines/video_llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/common/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/config.py -------------------------------------------------------------------------------- /baselines/video_llama/common/dist_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/dist_utils.py -------------------------------------------------------------------------------- /baselines/video_llama/common/gradcam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/gradcam.py -------------------------------------------------------------------------------- /baselines/video_llama/common/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/logger.py -------------------------------------------------------------------------------- /baselines/video_llama/common/optims.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/optims.py -------------------------------------------------------------------------------- /baselines/video_llama/common/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/registry.py -------------------------------------------------------------------------------- /baselines/video_llama/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/common/utils.py -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/cc_sbu/align.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/cc_sbu/align.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/cc_sbu/defaults.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/cc_sbu/defaults.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/instruct/llava_instruct.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/instruct/llava_instruct.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/instruct/webvid_instruct.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/instruct/webvid_instruct.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/laion/defaults.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/laion/defaults.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/datasets/webvid/defaults.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/datasets/webvid/defaults.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/default.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/models/minigpt4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/models/minigpt4.yaml -------------------------------------------------------------------------------- /baselines/video_llama/configs/models/video_llama.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/configs/models/video_llama.yaml -------------------------------------------------------------------------------- /baselines/video_llama/conversation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/conversation/conversation_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/conversation/conversation_video.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/datasets/builders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/builders/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/builders/base_dataset_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/builders/base_dataset_builder.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/builders/image_text_pair_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/builders/image_text_pair_builder.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/builders/instruct_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/builders/instruct_builder.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/builders/video_caption_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/builders/video_caption_builder.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/data_utils.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/base_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/base_dataset.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/caption_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/caption_datasets.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/cc_sbu_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/cc_sbu_dataset.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/dataloader_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/dataloader_utils.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/laion_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/laion_dataset.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/llava_instruct_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/llava_instruct_dataset.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/video_instruct_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/video_instruct_dataset.py -------------------------------------------------------------------------------- /baselines/video_llama/datasets/datasets/webvid_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/datasets/datasets/webvid_datasets.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/bird_audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/bird_audio.wav -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/bird_image.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/bird_image.jpg -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/car_audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/car_audio.wav -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/car_image.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/car_image.jpg -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/dog_audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/dog_audio.wav -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/.assets/dog_image.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/.assets/dog_image.jpg -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/CONTRIBUTING.md -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/LICENSE -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/README.md -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/bpe/bpe_simple_vocab_16e6.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/bpe/bpe_simple_vocab_16e6.txt.gz -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/data.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/model_card.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/model_card.md -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/models/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/models/helpers.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/models/imagebind_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/models/imagebind_model.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/models/multimodal_preprocessors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/models/multimodal_preprocessors.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/models/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/models/transformer.py -------------------------------------------------------------------------------- /baselines/video_llama/models/ImageBind/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/ImageBind/requirements.txt -------------------------------------------------------------------------------- /baselines/video_llama/models/Qformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/Qformer.py -------------------------------------------------------------------------------- /baselines/video_llama/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/models/base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/base_model.py -------------------------------------------------------------------------------- /baselines/video_llama/models/blip2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/blip2.py -------------------------------------------------------------------------------- /baselines/video_llama/models/blip2_outputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/blip2_outputs.py -------------------------------------------------------------------------------- /baselines/video_llama/models/eva_vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/eva_vit.py -------------------------------------------------------------------------------- /baselines/video_llama/models/modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/modeling_llama.py -------------------------------------------------------------------------------- /baselines/video_llama/models/video_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/models/video_llama.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/base_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/base_processor.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/blip_processors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/blip_processors.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/functional_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/functional_video.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/randaugment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/randaugment.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/transforms_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/transforms_video.py -------------------------------------------------------------------------------- /baselines/video_llama/processors/video_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/processors/video_processor.py -------------------------------------------------------------------------------- /baselines/video_llama/runners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/runners/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/runners/runner_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/runners/runner_base.py -------------------------------------------------------------------------------- /baselines/video_llama/runners/test.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/video_llama/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/tasks/__init__.py -------------------------------------------------------------------------------- /baselines/video_llama/tasks/base_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/tasks/base_task.py -------------------------------------------------------------------------------- /baselines/video_llama/tasks/image_text_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/tasks/image_text_pretrain.py -------------------------------------------------------------------------------- /baselines/video_llama/tasks/video_text_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/tasks/video_text_pretrain.py -------------------------------------------------------------------------------- /baselines/video_llama/video_llama_eval_withaudio.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/video_llama/video_llama_eval_withaudio.yaml -------------------------------------------------------------------------------- /baselines/videochat_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videochat_modeling.py -------------------------------------------------------------------------------- /baselines/videochatgpt_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videochatgpt_modeling.py -------------------------------------------------------------------------------- /baselines/videolavit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/videolavit/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/conversation.py -------------------------------------------------------------------------------- /baselines/videolavit/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/__init__.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_3d_unet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_3d_unet.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_decoder.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_motion_condition.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_motion_condition.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_motion_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_motion_tokenizer.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_transformer_temporal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_transformer_temporal.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_unet_3d_blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_unet_3d_blocks.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_video_lavit_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_video_lavit_hf.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_visual_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_visual_encoder.py -------------------------------------------------------------------------------- /baselines/videolavit/models/modeling_visual_tokenzier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/modeling_visual_tokenzier.py -------------------------------------------------------------------------------- /baselines/videolavit/models/transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/transform.py -------------------------------------------------------------------------------- /baselines/videolavit/models/video_detokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/video_detokenizer.py -------------------------------------------------------------------------------- /baselines/videolavit/models/video_lavit_for_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/video_lavit_for_generation.py -------------------------------------------------------------------------------- /baselines/videolavit/models/video_lavit_for_understanding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/models/video_lavit_for_understanding.py -------------------------------------------------------------------------------- /baselines/videolavit/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit/utils.py -------------------------------------------------------------------------------- /baselines/videolavit_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videolavit_modeling.py -------------------------------------------------------------------------------- /baselines/videollama2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/__init__.py -------------------------------------------------------------------------------- /baselines/videollama2/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/constants.py -------------------------------------------------------------------------------- /baselines/videollama2/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/conversation.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_TUT2017.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_TUT2017.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_clotho.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_clotho.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_clothoAQA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_clothoAQA.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_video_AVQA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_video_AVQA.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_video_AVSD.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_video_AVSD.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_video_AVSSD.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_video_AVSSD.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_audio_vocalsound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_audio_vocalsound.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_cap_msvc_correctness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_cap_msvc_correctness.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_cap_msvc_detailedness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_cap_msvc_detailedness.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_mcqa_mvbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_mcqa_mvbench.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_mcqa_videomme.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_mcqa_videomme.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_activitynet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_activitynet.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_vcgpt_1_correctness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_vcgpt_1_correctness.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_vcgpt_2_detailed_orientation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_vcgpt_2_detailed_orientation.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_vcgpt_3_context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_vcgpt_3_context.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_vcgpt_4_temporal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_vcgpt_4_temporal.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/eval_video_oqa_vcgpt_5_consistency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/eval_video_oqa_vcgpt_5_consistency.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_audio.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_audio_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_audio_video.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_cap_msvc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_cap_msvc.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_mcqa_egoschema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_mcqa_egoschema.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_mcqa_mvbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_mcqa_mvbench.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_mcqa_perception_test_mcqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_mcqa_perception_test_mcqa.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_mcqa_videomme.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_mcqa_videomme.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_oqa_activitynet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_oqa_activitynet.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_oqa_vcgpt_consistency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_oqa_vcgpt_consistency.py -------------------------------------------------------------------------------- /baselines/videollama2/eval/inference_video_oqa_vcgpt_general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/eval/inference_video_oqa_vcgpt_general.py -------------------------------------------------------------------------------- /baselines/videollama2/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/mm_utils.py -------------------------------------------------------------------------------- /baselines/videollama2/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/__init__.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/BEATs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/BEATs.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/LICENSE_beats: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/LICENSE_beats -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/Tokenizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/Tokenizers.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/backbone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/backbone.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/modules.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/quantizer.py -------------------------------------------------------------------------------- /baselines/videollama2/model/beats/weight_norm_fix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/beats/weight_norm_fix.py -------------------------------------------------------------------------------- /baselines/videollama2/model/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/encoder.py -------------------------------------------------------------------------------- /baselines/videollama2/model/mel_filters.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/mel_filters.npz -------------------------------------------------------------------------------- /baselines/videollama2/model/projector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/projector.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_arch.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_gemma2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_gemma2.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_llama.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_mistral.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_mixtral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_mixtral.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_phi3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_phi3.py -------------------------------------------------------------------------------- /baselines/videollama2/model/videollama2_qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/model/videollama2_qwen2.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/cli.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/controller.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/examples/bird-twitter-car.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/examples/bird-twitter-car.wav -------------------------------------------------------------------------------- /baselines/videollama2/serve/examples/desert.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/examples/desert.jpg -------------------------------------------------------------------------------- /baselines/videollama2/serve/examples/door.of.bar.raining2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/examples/door.of.bar.raining2.wav -------------------------------------------------------------------------------- /baselines/videollama2/serve/examples/extreme_ironing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/examples/extreme_ironing.jpg -------------------------------------------------------------------------------- /baselines/videollama2/serve/examples/waterview.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/examples/waterview.jpg -------------------------------------------------------------------------------- /baselines/videollama2/serve/gradio_web_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/gradio_web_server.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/gradio_web_server_adhoc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/gradio_web_server_adhoc.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/gradio_web_server_adhoc_av.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/gradio_web_server_adhoc_av.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/model_worker.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/register_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/register_worker.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/sglang_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/sglang_worker.py -------------------------------------------------------------------------------- /baselines/videollama2/serve/test_message.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/serve/test_message.py -------------------------------------------------------------------------------- /baselines/videollama2/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/train.py -------------------------------------------------------------------------------- /baselines/videollama2/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/utils.py -------------------------------------------------------------------------------- /baselines/videollama2/videollama2_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2/videollama2_trainer.py -------------------------------------------------------------------------------- /baselines/videollama2_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama2_modeling.py -------------------------------------------------------------------------------- /baselines/videollama_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollama_modeling.py -------------------------------------------------------------------------------- /baselines/videollava/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import LlavaLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /baselines/videollava/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/constants.py -------------------------------------------------------------------------------- /baselines/videollava/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/conversation.py -------------------------------------------------------------------------------- /baselines/videollava/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/mm_utils.py -------------------------------------------------------------------------------- /baselines/videollava/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/__init__.py -------------------------------------------------------------------------------- /baselines/videollava/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/apply_delta.py -------------------------------------------------------------------------------- /baselines/videollava/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/builder.py -------------------------------------------------------------------------------- /baselines/videollava/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/consolidate.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/llava_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/llava_llama.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/llava_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/llava_mpt.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/adapt_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/adapt_tokenizer.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/attention.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/blocks.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/configuration_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/configuration_mpt.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/custom_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/custom_embedding.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/flash_attn_triton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/flash_attn_triton.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/hf_prefixlm_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/hf_prefixlm_converter.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/meta_init_context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/meta_init_context.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/modeling_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/modeling_mpt.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/norm.py -------------------------------------------------------------------------------- /baselines/videollava/model/language_model/mpt/param_init_fns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/language_model/mpt/param_init_fns.py -------------------------------------------------------------------------------- /baselines/videollava/model/llava_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/llava_arch.py -------------------------------------------------------------------------------- /baselines/videollava/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/make_delta.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/__init__.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/audio/configuration_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/audio/configuration_audio.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/audio/modeling_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/audio/modeling_audio.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/audio/processing_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/audio/processing_audio.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/audio/tokenization_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/audio/tokenization_audio.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/depth/configuration_depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/depth/configuration_depth.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/depth/modeling_depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/depth/modeling_depth.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/depth/tokenization_depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/depth/tokenization_depth.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/image/configuration_image.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/image/configuration_image.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/image/modeling_image.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/image/modeling_image.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/image/processing_image.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/image/processing_image.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/image/tokenization_image.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/image/tokenization_image.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/thermal/configuration_thermal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/thermal/configuration_thermal.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/thermal/modeling_thermal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/thermal/modeling_thermal.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/thermal/processing_thermal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/thermal/processing_thermal.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/thermal/tokenization_thermal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/thermal/tokenization_thermal.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/video/configuration_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/video/configuration_video.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/video/modeling_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/video/modeling_video.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/video/processing_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/video/processing_video.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_encoder/languagebind/video/tokenization_video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_encoder/languagebind/video/tokenization_video.py -------------------------------------------------------------------------------- /baselines/videollava/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /baselines/videollava/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/model/utils.py -------------------------------------------------------------------------------- /baselines/videollava/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava/utils.py -------------------------------------------------------------------------------- /baselines/videollava_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/baselines/videollava_modeling.py -------------------------------------------------------------------------------- /evaluations/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation.py -------------------------------------------------------------------------------- /evaluations/evaluation_bias.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_bias.py -------------------------------------------------------------------------------- /evaluations/evaluation_bias_sep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_bias_sep.py -------------------------------------------------------------------------------- /evaluations/evaluation_halluc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_halluc.py -------------------------------------------------------------------------------- /evaluations/evaluation_pep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_pep.py -------------------------------------------------------------------------------- /evaluations/evaluation_pep_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_pep_utils.py -------------------------------------------------------------------------------- /evaluations/evaluation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/evaluations/evaluation_utils.py -------------------------------------------------------------------------------- /model_testing_zoo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/model_testing_zoo.py -------------------------------------------------------------------------------- /videohallucer_datasets/external_factual/external_factual.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/external_factual/external_factual.json -------------------------------------------------------------------------------- /videohallucer_datasets/external_nonfactual/external_nonfactual.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/external_nonfactual/external_nonfactual.json -------------------------------------------------------------------------------- /videohallucer_datasets/fact_detect/fact_detect.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/fact_detect/fact_detect.json -------------------------------------------------------------------------------- /videohallucer_datasets/fact_detect/fact_detect_yn.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/fact_detect/fact_detect_yn.json -------------------------------------------------------------------------------- /videohallucer_datasets/fact_detect/modify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/fact_detect/modify.py -------------------------------------------------------------------------------- /videohallucer_datasets/interaction/conflict.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/interaction/conflict.jsonl -------------------------------------------------------------------------------- /videohallucer_datasets/interaction/interaction.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/interaction/interaction.json -------------------------------------------------------------------------------- /videohallucer_datasets/interaction/stat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/interaction/stat.py -------------------------------------------------------------------------------- /videohallucer_datasets/object_relation/object_relation.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/object_relation/object_relation.json -------------------------------------------------------------------------------- /videohallucer_datasets/semantic_detail/semantic_detail.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/semantic_detail/semantic_detail.json -------------------------------------------------------------------------------- /videohallucer_datasets/temporal/temporal.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/patrick-tssn/VideoHallucer/HEAD/videohallucer_datasets/temporal/temporal.json --------------------------------------------------------------------------------