PubMedCLIP
Fine-tuning CLIP using ROCO dataset which contains image-caption pairs from PubMed articles.
File Explorer
Download Latest Version (.zip)- Medical_VQA_Framework.png
- attention.py
- auto_encoder.py
- base_model.py
- bc.py
- classifier.py
- counting.py
- fc.py
- language_model.py
- main.py
- meters.py
- README.md
- run_clipOrg.sh
- run_pubmedclip.sh
- simple_cnn.py
- test.py
- train.py
- trainer.py
- utils.py
- medclip_roco_all.yaml
- medclip_roco_all_resnet50.yaml
- medclip_roco_all_resnet50x4.yaml
- __init__.py
- default.py
- __init__.py
- evaluate.py
- function.py
- __init__.py
- transform_wrapper.py
- __init__.py
- ROCOdataset.py
- __init__.py
- registry.py
- utils.py
- _init_paths.py
- create_jsons.py
- main.py
- train.py
- README.md
- requirements.txt
- run.sh
- qcr_clipOrgRN50_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_clipOrgRN50_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- qcr_clipOrgRN50x4_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_clipOrgRN50x4_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- qcr_clipOrgViT_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_clipOrgViT_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipRN50_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipRN50_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipRN50x4_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipRN50x4_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipViT_ae_rad_16batchsize_withtfidf_nondeterministic.yaml
- qcr_pubmedclipViT_ae_slake_16batchsize_withtfidf_nondeterministic.yaml
- __init__.py
- multi_level_model.py
- __init__.py
- default.py
- combiner.py
- __init__.py
- dataset_RAD.py
- dataset_SLAKE.py
- __init__.py
- classify_question.py
- language_model.py
- __init__.py
- auto_encoder.py
- connect.py
- counting.py
- maml.py
- network.py
- __init__.py
- create_dictionary.py
- create_img2idx.py
- create_label.py
- create_resized_images.py
- README.md
- run.sh
- utils.py
- _init_paths.py
- classifier.py
- language_model.py
- main.py
- test.py
- train.py
- type_classifier.py
- type_classifier.pth
- type_classifier_slake.pth
- README.md
- run_clipOrg_ae.sh
- run_pubmedclip_ae.sh
- .gitignore
- LICENSE
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/sarahESL/PubMedCLIP
Downloads the entire project code from GitHub to your computer.
cd PubMedCLIP
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -r PubMedCLIP/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python <μ€νν νμΌλͺ
>.py # READMEμμ μ νν μ€ν νμΌλͺ
μ νμΈνμΈμ
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
// repository documentation
Was this content helpful?
(0 ratings)
