├── .gitignore ├── LICENSE ├── README.md ├── README_QWEN.md ├── README_TASKIT.md ├── assets ├── demo_input.jpg ├── demo_output.png ├── notebook-images │ ├── classify_1.JPEG │ ├── classify_2.JPEG │ ├── classify_3.JPEG │ ├── detect_1.jpg │ ├── group_1.jpg │ ├── group_2.jpg │ ├── room.png │ ├── room_2.png │ └── segment_1.jpg ├── obj_det_method.svg ├── pull_figure.svg └── script-images │ ├── input │ ├── 000000000785.jpg │ ├── 000000344100.jpg │ ├── classify_1.jpg │ ├── classify_2.jpg │ ├── grouping_1.jpg │ ├── grouping_2.jpg │ ├── room_1.png │ ├── room_2.png │ ├── segment_1.jpg │ └── segment_2.jpg │ └── output │ ├── depth_1.png │ ├── depth_2.png │ ├── normals_1.png │ ├── normals_2.png │ ├── segment_1.png │ └── segment_2.png ├── notebooks └── demo.ipynb ├── requirements.txt ├── scripts ├── data │ └── files │ │ ├── classify.txt │ │ ├── dataset-files │ │ ├── coco-detect.txt │ │ ├── coco-group-100.txt │ │ ├── coco-segment-500.txt │ │ ├── hypersim-100.txt │ │ ├── imagenet-class.txt │ │ ├── imagenet-r.txt │ │ ├── imagenet-robustbench-2dcc-50k.txt │ │ ├── imagenet-robustbench-3dcc-45k.txt │ │ ├── imagenet-sketch.txt │ │ ├── imagenet-v2.txt │ │ └── reasoning-subset │ │ │ ├── reasoning-coco-detect-200.txt │ │ │ ├── reasoning-coco-group-30.txt │ │ │ ├── reasoning-coco-segment-50.txt │ │ │ ├── reasoning-hypersim-depth-10.txt │ │ │ ├── reasoning-hypersim-normals-10.txt │ │ │ ├── reasoning-imagenet-1k_samples.txt │ │ │ ├── reasoning-imagenet-r-1k_samples.txt │ │ │ ├── reasoning-imagenet-robustbench-2dcc-50k-1k_samples.txt │ │ │ ├── reasoning-imagenet-robustbench-3dcc-45k-1k_samples.txt │ │ │ ├── reasoning-imagenet-sketch-1k_samples.txt │ │ │ └── reasoning-imagenet-v2-1k_samples.txt │ │ ├── depth.txt │ │ ├── grouping.txt │ │ ├── normals.txt │ │ ├── object.txt │ │ └── segment.txt ├── infer.py ├── metadata │ ├── benchmark-gt │ │ ├── coco-segment.json │ │ ├── hypersim-depth.json │ │ ├── hypersim-normals.json │ │ ├── imagenet-r.json │ │ ├── imagenet-robustbench-2dcc.json │ │ ├── imagenet-robustbench-3dcc.json │ │ ├── imagenet-sketch.json │ │ ├── imagenet-v2.json │ │ └── imagenet.json │ ├── classify.json │ ├── depth.json │ ├── grouping.json │ ├── normals.json │ ├── object.json │ └── segment.json ├── run_qwen_backend.py └── utils │ └── log.py └── taskit ├── __init__.py ├── demo.py ├── eval ├── __init__.py ├── eval_classify.py ├── eval_depth.py ├── eval_grouping.py ├── eval_normals.py ├── eval_object.py ├── eval_segment.py └── eval_utils.py ├── mfm.py ├── mfm_configs.py ├── tasks ├── __init__.py ├── classify.py ├── depth.py ├── grouping.py ├── normals.py ├── object.py └── segment.py └── utils ├── data.py └── data_constants.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/README.md -------------------------------------------------------------------------------- /README_QWEN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/README_QWEN.md -------------------------------------------------------------------------------- /README_TASKIT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/README_TASKIT.md -------------------------------------------------------------------------------- /assets/demo_input.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/demo_input.jpg -------------------------------------------------------------------------------- /assets/demo_output.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/demo_output.png -------------------------------------------------------------------------------- /assets/notebook-images/classify_1.JPEG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/classify_1.JPEG -------------------------------------------------------------------------------- /assets/notebook-images/classify_2.JPEG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/classify_2.JPEG -------------------------------------------------------------------------------- /assets/notebook-images/classify_3.JPEG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/classify_3.JPEG -------------------------------------------------------------------------------- /assets/notebook-images/detect_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/detect_1.jpg -------------------------------------------------------------------------------- /assets/notebook-images/group_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/group_1.jpg -------------------------------------------------------------------------------- /assets/notebook-images/group_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/group_2.jpg -------------------------------------------------------------------------------- /assets/notebook-images/room.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/room.png -------------------------------------------------------------------------------- /assets/notebook-images/room_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/room_2.png -------------------------------------------------------------------------------- /assets/notebook-images/segment_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/notebook-images/segment_1.jpg -------------------------------------------------------------------------------- /assets/obj_det_method.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/obj_det_method.svg -------------------------------------------------------------------------------- /assets/pull_figure.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/pull_figure.svg -------------------------------------------------------------------------------- /assets/script-images/input/000000000785.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/000000000785.jpg -------------------------------------------------------------------------------- /assets/script-images/input/000000344100.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/000000344100.jpg -------------------------------------------------------------------------------- /assets/script-images/input/classify_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/classify_1.jpg -------------------------------------------------------------------------------- /assets/script-images/input/classify_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/classify_2.jpg -------------------------------------------------------------------------------- /assets/script-images/input/grouping_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/grouping_1.jpg -------------------------------------------------------------------------------- /assets/script-images/input/grouping_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/grouping_2.jpg -------------------------------------------------------------------------------- /assets/script-images/input/room_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/room_1.png -------------------------------------------------------------------------------- /assets/script-images/input/room_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/room_2.png -------------------------------------------------------------------------------- /assets/script-images/input/segment_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/segment_1.jpg -------------------------------------------------------------------------------- /assets/script-images/input/segment_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/input/segment_2.jpg -------------------------------------------------------------------------------- /assets/script-images/output/depth_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/depth_1.png -------------------------------------------------------------------------------- /assets/script-images/output/depth_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/depth_2.png -------------------------------------------------------------------------------- /assets/script-images/output/normals_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/normals_1.png -------------------------------------------------------------------------------- /assets/script-images/output/normals_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/normals_2.png -------------------------------------------------------------------------------- /assets/script-images/output/segment_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/segment_1.png -------------------------------------------------------------------------------- /assets/script-images/output/segment_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/assets/script-images/output/segment_2.png -------------------------------------------------------------------------------- /notebooks/demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/notebooks/demo.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/data/files/classify.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/classify.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/coco-detect.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/coco-detect.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/coco-group-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/coco-group-100.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/coco-segment-500.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/coco-segment-500.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/hypersim-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/hypersim-100.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-class.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-class.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-r.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-r.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-robustbench-2dcc-50k.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-robustbench-2dcc-50k.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-robustbench-3dcc-45k.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-robustbench-3dcc-45k.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-sketch.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-sketch.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/imagenet-v2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/imagenet-v2.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-detect-200.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-detect-200.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-group-30.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-group-30.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-segment-50.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-coco-segment-50.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-hypersim-depth-10.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-hypersim-depth-10.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-hypersim-normals-10.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-hypersim-normals-10.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-r-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-r-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-robustbench-2dcc-50k-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-robustbench-2dcc-50k-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-robustbench-3dcc-45k-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-robustbench-3dcc-45k-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-sketch-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-sketch-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-v2-1k_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/dataset-files/reasoning-subset/reasoning-imagenet-v2-1k_samples.txt -------------------------------------------------------------------------------- /scripts/data/files/depth.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/depth.txt -------------------------------------------------------------------------------- /scripts/data/files/grouping.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/grouping.txt -------------------------------------------------------------------------------- /scripts/data/files/normals.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/normals.txt -------------------------------------------------------------------------------- /scripts/data/files/object.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/object.txt -------------------------------------------------------------------------------- /scripts/data/files/segment.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/data/files/segment.txt -------------------------------------------------------------------------------- /scripts/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/infer.py -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/coco-segment.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/coco-segment.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/hypersim-depth.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/hypersim-depth.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/hypersim-normals.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/hypersim-normals.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet-r.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet-r.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet-robustbench-2dcc.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet-robustbench-2dcc.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet-robustbench-3dcc.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet-robustbench-3dcc.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet-sketch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet-sketch.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet-v2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet-v2.json -------------------------------------------------------------------------------- /scripts/metadata/benchmark-gt/imagenet.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/benchmark-gt/imagenet.json -------------------------------------------------------------------------------- /scripts/metadata/classify.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/classify.json -------------------------------------------------------------------------------- /scripts/metadata/depth.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/depth.json -------------------------------------------------------------------------------- /scripts/metadata/grouping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/grouping.json -------------------------------------------------------------------------------- /scripts/metadata/normals.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/normals.json -------------------------------------------------------------------------------- /scripts/metadata/object.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/object.json -------------------------------------------------------------------------------- /scripts/metadata/segment.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/metadata/segment.json -------------------------------------------------------------------------------- /scripts/run_qwen_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/run_qwen_backend.py -------------------------------------------------------------------------------- /scripts/utils/log.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/scripts/utils/log.py -------------------------------------------------------------------------------- /taskit/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/__init__.py -------------------------------------------------------------------------------- /taskit/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/demo.py -------------------------------------------------------------------------------- /taskit/eval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/__init__.py -------------------------------------------------------------------------------- /taskit/eval/eval_classify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_classify.py -------------------------------------------------------------------------------- /taskit/eval/eval_depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_depth.py -------------------------------------------------------------------------------- /taskit/eval/eval_grouping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_grouping.py -------------------------------------------------------------------------------- /taskit/eval/eval_normals.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_normals.py -------------------------------------------------------------------------------- /taskit/eval/eval_object.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_object.py -------------------------------------------------------------------------------- /taskit/eval/eval_segment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_segment.py -------------------------------------------------------------------------------- /taskit/eval/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/eval/eval_utils.py -------------------------------------------------------------------------------- /taskit/mfm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/mfm.py -------------------------------------------------------------------------------- /taskit/mfm_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/mfm_configs.py -------------------------------------------------------------------------------- /taskit/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/__init__.py -------------------------------------------------------------------------------- /taskit/tasks/classify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/classify.py -------------------------------------------------------------------------------- /taskit/tasks/depth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/depth.py -------------------------------------------------------------------------------- /taskit/tasks/grouping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/grouping.py -------------------------------------------------------------------------------- /taskit/tasks/normals.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/normals.py -------------------------------------------------------------------------------- /taskit/tasks/object.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/object.py -------------------------------------------------------------------------------- /taskit/tasks/segment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/tasks/segment.py -------------------------------------------------------------------------------- /taskit/utils/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/utils/data.py -------------------------------------------------------------------------------- /taskit/utils/data_constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EPFL-VILAB/fm-vision-evals/HEAD/taskit/utils/data_constants.py --------------------------------------------------------------------------------