Skip to content

GuanshuoXu/RSNA-STR-Pulmonary-Embolism-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RSNA-STR-Pulmonary-Embolism-Detection

Link to method description: https://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/194145

Software Requirement: torch 1.3.1 torchvision 0.4.2 pydicom 2.0.0 pandas 1.0.3 numpy 1.17.2 gdcm 2.8.9 apex 0.1 huggingface transformers 2.11.0 imgaug

Following libraries are used in my code but not required to install: https://github.com/Cadene/pretrained-models.pytorch https://github.com/lukemelas/EfficientNet-PyTorch https://github.com/albumentations-team/albumentations

Hardware Requirement: I used 4 x RTX Titan for image-level model training, and 1 x 2070 for study-level training.

For local validation, go to trainval/ and sh run.sh

To retrain on the full training data, go to trainall/ and sh run.sh

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages