├── .gitignore ├── README.md ├── clip ├── dataset_config.json ├── dataset_process │ └── quit_to_web_dataset.py ├── init.py ├── script │ ├── run_few_shot_eval.sh │ ├── run_retrieval_eval.sh │ ├── run_webdataset.sh │ └── run_zero_shot_eval.sh └── val │ ├── few_shot_evaluation.py │ ├── retrieval_evaluation.py │ └── zero_shot_evaluation.py ├── data ├── ImageTextExtraction │ ├── LMBased │ │ ├── README.md │ │ ├── alignment.py │ │ ├── crop.py │ │ ├── inline_async.py │ │ ├── layout_async.py │ │ ├── main.py │ │ ├── output │ │ │ ├── crops │ │ │ │ ├── 0001_fig0.jpg │ │ │ │ ├── 0001_fig1.jpg │ │ │ │ ├── 0002_fig0.jpg │ │ │ │ ├── 0002_fig1.jpg │ │ │ │ ├── 0002_fig2.jpg │ │ │ │ ├── 0002_fig3.jpg │ │ │ │ ├── 0003_fig0.jpg │ │ │ │ └── 0003_fig1.jpg │ │ │ ├── high_res │ │ │ │ ├── 0001.jpg │ │ │ │ ├── 0002.jpg │ │ │ │ ├── 0003.jpg │ │ │ │ └── 0004.jpg │ │ │ ├── images │ │ │ │ ├── 0001.jpg │ │ │ │ ├── 0001_ali.json │ │ │ │ ├── 0001_main.txt │ │ │ │ ├── 0002.jpg │ │ │ │ ├── 0002_ali.json │ │ │ │ ├── 0002_main.txt │ │ │ │ ├── 0003.jpg │ │ │ │ ├── 0003_ali.json │ │ │ │ ├── 0003_main.txt │ │ │ │ ├── 0004.jpg │ │ │ │ ├── 0004_none.json │ │ │ │ └── done.txt │ │ │ ├── layout │ │ │ │ ├── 0001.json │ │ │ │ ├── 0001 │ │ │ │ │ ├── 0001_fig0.jpg │ │ │ │ │ ├── 0001_fig0.txt │ │ │ │ │ ├── 0001_fig1.jpg │ │ │ │ │ ├── 0001_fig1.txt │ │ │ │ │ ├── 0001_fig11.jpg │ │ │ │ │ ├── 0001_fig11.txt │ │ │ │ │ ├── 0001_fig12.jpg │ │ │ │ │ ├── 0001_fig12.txt │ │ │ │ │ ├── 0001_fig13.jpg │ │ │ │ │ ├── 0001_fig13.txt │ │ │ │ │ ├── 0001_fig18.jpg │ │ │ │ │ ├── 0001_fig18.txt │ │ │ │ │ ├── 0001_fig2.jpg │ │ │ │ │ ├── 0001_fig2.txt │ │ │ │ │ ├── 0001_fig3.jpg │ │ │ │ │ ├── 0001_fig3.txt │ │ │ │ │ ├── 0001_fig8.jpg │ │ │ │ │ └── 0001_fig8.txt │ │ │ │ ├── 0002.json │ │ │ │ ├── 0002 │ │ │ │ │ ├── 0002_fig0.jpg │ │ │ │ │ ├── 0002_fig0.txt │ │ │ │ │ ├── 0002_fig1.jpg │ │ │ │ │ ├── 0002_fig1.txt │ │ │ │ │ ├── 0002_fig10.jpg │ │ │ │ │ ├── 0002_fig10.txt │ │ │ │ │ ├── 0002_fig12.jpg │ │ │ │ │ ├── 0002_fig12.txt │ │ │ │ │ ├── 0002_fig4.jpg │ │ │ │ │ ├── 0002_fig4.txt │ │ │ │ │ ├── 0002_fig5.jpg │ │ │ │ │ └── 0002_fig5.txt │ │ │ │ ├── 0003.json │ │ │ │ ├── 0003 │ │ │ │ │ ├── 0003_fig1.jpg │ │ │ │ │ ├── 0003_fig1.txt │ │ │ │ │ ├── 0003_fig12.jpg │ │ │ │ │ ├── 0003_fig12.txt │ │ │ │ │ ├── 0003_fig15.jpg │ │ │ │ │ ├── 0003_fig15.txt │ │ │ │ │ ├── 0003_fig2.jpg │ │ │ │ │ ├── 0003_fig2.txt │ │ │ │ │ ├── 0003_fig3.jpg │ │ │ │ │ ├── 0003_fig3.txt │ │ │ │ │ ├── 0003_fig4.jpg │ │ │ │ │ └── 0003_fig4.txt │ │ │ │ ├── 0004.json │ │ │ │ └── 0004 │ │ │ │ │ ├── 0004_fig0.jpg │ │ │ │ │ ├── 0004_fig1.jpg │ │ │ │ │ ├── 0004_fig10.jpg │ │ │ │ │ ├── 0004_fig11.jpg │ │ │ │ │ ├── 0004_fig13.jpg │ │ │ │ │ ├── 0004_fig16.jpg │ │ │ │ │ ├── 0004_fig19.jpg │ │ │ │ │ ├── 0004_fig2.jpg │ │ │ │ │ ├── 0004_fig23.jpg │ │ │ │ │ ├── 0004_fig3.jpg │ │ │ │ │ ├── 0004_fig4.jpg │ │ │ │ │ ├── 0004_fig5.jpg │ │ │ │ │ ├── 0004_fig6.jpg │ │ │ │ │ ├── 0004_fig7.jpg │ │ │ │ │ └── 0004_fig9.jpg │ │ │ └── results │ │ │ │ └── result.json │ │ ├── pdf2img.py │ │ ├── prompts.py │ │ └── tools.py │ └── test.pdf └── example.jpg ├── docs └── overview.png ├── images └── example.jpg ├── r1 └── init.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/README.md -------------------------------------------------------------------------------- /clip/dataset_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/dataset_config.json -------------------------------------------------------------------------------- /clip/dataset_process/quit_to_web_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/dataset_process/quit_to_web_dataset.py -------------------------------------------------------------------------------- /clip/init.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /clip/script/run_few_shot_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/script/run_few_shot_eval.sh -------------------------------------------------------------------------------- /clip/script/run_retrieval_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/script/run_retrieval_eval.sh -------------------------------------------------------------------------------- /clip/script/run_webdataset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/script/run_webdataset.sh -------------------------------------------------------------------------------- /clip/script/run_zero_shot_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/script/run_zero_shot_eval.sh -------------------------------------------------------------------------------- /clip/val/few_shot_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/val/few_shot_evaluation.py -------------------------------------------------------------------------------- /clip/val/retrieval_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/val/retrieval_evaluation.py -------------------------------------------------------------------------------- /clip/val/zero_shot_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/clip/val/zero_shot_evaluation.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/README.md -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/alignment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/alignment.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/crop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/crop.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/inline_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/inline_async.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/layout_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/layout_async.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/main.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0001_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0001_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0001_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0001_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0002_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0002_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0002_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0002_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0002_fig2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0002_fig2.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0002_fig3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0002_fig3.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0003_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0003_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/crops/0003_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/crops/0003_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/high_res/0001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/high_res/0001.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/high_res/0002.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/high_res/0002.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/high_res/0003.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/high_res/0003.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/high_res/0004.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/high_res/0004.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0001.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0001_ali.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0001_ali.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0001_main.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0001_main.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0002.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0002.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0002_ali.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0002_ali.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0002_main.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0002_main.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0003.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0003.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0003_ali.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0003_ali.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0003_main.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0003_main.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0004.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/0004.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/0004_none.json: -------------------------------------------------------------------------------- 1 | [] -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/images/done.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/images/done.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig0.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig0.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig1.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig11.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig11.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig11.txt: -------------------------------------------------------------------------------- 1 | (步宏) -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig12.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig12.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig12.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig12.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig13.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig13.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig13.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig13.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig18.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig18.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig18.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig18.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig2.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig2.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig3.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig3.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig8.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig8.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig8.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0001/0001_fig8.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig0.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig0.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig1.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig10.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig10.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig10.txt: -------------------------------------------------------------------------------- 1 | 【鉴别诊断】良性叶状肿瘤。 -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig12.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig12.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig12.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig12.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig4.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig4.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig5.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig5.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0002/0002_fig5.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig1.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig12.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig12.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig12.txt: -------------------------------------------------------------------------------- 1 | (步宏) -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig15.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig15.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig15.txt: -------------------------------------------------------------------------------- 1 | A.肿瘤浸润性边缘;B.间质梭形细胞具有显著异型性,易见核分裂象。 -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig2.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig2.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig3.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig3.txt -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig4.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0003/0003_fig4.txt: -------------------------------------------------------------------------------- 1 | 乳腺错构瘤(hamartoma of the breast)是由异源性乳腺组织构成的病变,可发生于任何年龄。 -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig0.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig1.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig10.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig10.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig11.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig11.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig13.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig13.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig16.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig16.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig19.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig19.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig2.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig23.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig23.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig3.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig4.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig5.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig5.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig6.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig6.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig7.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig7.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig9.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/layout/0004/0004_fig9.jpg -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/output/results/result.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/output/results/result.json -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/pdf2img.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/pdf2img.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/prompts.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/LMBased/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/LMBased/tools.py -------------------------------------------------------------------------------- /data/ImageTextExtraction/test.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/ImageTextExtraction/test.pdf -------------------------------------------------------------------------------- /data/example.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/data/example.jpg -------------------------------------------------------------------------------- /docs/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/docs/overview.png -------------------------------------------------------------------------------- /images/example.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/images/example.jpg -------------------------------------------------------------------------------- /r1/init.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wenchuan-Zhang/Patho-R1/HEAD/requirements.txt --------------------------------------------------------------------------------