├── .gitignore ├── README.md ├── checkpoints └── .gitkeep ├── config ├── config.yml └── data_config.yml ├── data └── master_labels.txt ├── data_wrangling ├── README.md ├── dataset.py ├── pickle_data.py ├── render_data.py └── split_data.py ├── eval └── eval.py ├── generate_dataset.sh ├── generate_pickles.sh ├── model ├── __init__.py ├── attention.py ├── decoder.py ├── encoder.py ├── ocr_model.py └── resnet.py ├── requirements.txt ├── test.py ├── tokenizer ├── __init__.py ├── special_tokens.txt ├── tokenizer.py └── tokenizer_clean_1k.txt ├── train.py ├── train_tokenizer.sh └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/README.md -------------------------------------------------------------------------------- /checkpoints/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /config/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/config/config.yml -------------------------------------------------------------------------------- /config/data_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/config/data_config.yml -------------------------------------------------------------------------------- /data/master_labels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data/master_labels.txt -------------------------------------------------------------------------------- /data_wrangling/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data_wrangling/README.md -------------------------------------------------------------------------------- /data_wrangling/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data_wrangling/dataset.py -------------------------------------------------------------------------------- /data_wrangling/pickle_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data_wrangling/pickle_data.py -------------------------------------------------------------------------------- /data_wrangling/render_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data_wrangling/render_data.py -------------------------------------------------------------------------------- /data_wrangling/split_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/data_wrangling/split_data.py -------------------------------------------------------------------------------- /eval/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/eval/eval.py -------------------------------------------------------------------------------- /generate_dataset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/generate_dataset.sh -------------------------------------------------------------------------------- /generate_pickles.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/generate_pickles.sh -------------------------------------------------------------------------------- /model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/__init__.py -------------------------------------------------------------------------------- /model/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/attention.py -------------------------------------------------------------------------------- /model/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/decoder.py -------------------------------------------------------------------------------- /model/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/encoder.py -------------------------------------------------------------------------------- /model/ocr_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/ocr_model.py -------------------------------------------------------------------------------- /model/resnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/model/resnet.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | torch 2 | timm -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/test.py -------------------------------------------------------------------------------- /tokenizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/tokenizer/__init__.py -------------------------------------------------------------------------------- /tokenizer/special_tokens.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/tokenizer/special_tokens.txt -------------------------------------------------------------------------------- /tokenizer/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/tokenizer/tokenizer.py -------------------------------------------------------------------------------- /tokenizer/tokenizer_clean_1k.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/tokenizer/tokenizer_clean_1k.txt -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/train.py -------------------------------------------------------------------------------- /train_tokenizer.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/train_tokenizer.sh -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/olibridge01/TeXOCR/HEAD/utils.py --------------------------------------------------------------------------------