Inicio Explorar Axuda
Iniciar sesión
schuurs
/
Pytorch_CNN-RNN
1
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki

Ali's CNN+RNN code rewritten from tensorflow into pytorch

Árbore: ad21d569c0
Ramas Etiquetas
Pytorch_CNN-...
ZIP TAR.GZ
Ruben Aguilo Schuurs ad21d569c0 Small update for Andrej use hai 5 meses
PET_volumes_customtemplate_float32 548d466ee7 clinical data version finished hai 1 ano
figures f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
original_model f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
utils f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
.gitignore 99ebbe9235 Added gitignore hai 1 ano
LP_ADNIMERGE.csv 1335d846e1 Initial commit, added all files and initial progress hai 1 ano
README ad21d569c0 Small update for Andrej use hai 5 meses
ROC_2024-08-13_14.36.png f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
TALOS_main.py 12ba1c5f54 New runs, failed TALOS attempt, preparing remote work for data augmentation and normalization hai 10 meses
avgloss_epoch_curve_2024-08-13_14.36.png f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
cnn_net.pth f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
cnn_net_data_2024-08-13_14.36.csv f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
confusion_matrix_2024-08-13_14.36.png f140373ea3 First, unsuccessful attempt at GuidedGradCam. Trained new model & removed clinical data temporarily hai 10 meses
main.py ad21d569c0 Small update for Andrej use hai 5 meses

README

Pytorch CNN model to diagnose Alzheimer's Disease on PET Scans
PyTorch version Ruben Aguilo Schuurs (UW-Madison), reworked from Dr. Alison Deatsch's Tensorflow Version

Files:
- main.py: Controls everything. Calls all of the following files
- utils/CNN.py & utils/CNN_Layers.py: CNN Model structure
- preprocess.py: prepares CustomDatasets training, validation, and testing
- train_methods.py: CNN training code
- Graphs.py: Multiple graphing / results functions
- K-fold.py: Specific graphs
- dataset_sd_mean_finder.py: unused
- show_image.py: show image
- TALOS_main.py: unsuccessful attempt at implementing talos

To run (in main.py):
1. Define the CNN filepath and dataset filepath
2. Change the properties
3. Comment or uncomment the functions (train, load, evaluate, predict) depending on your interest.
-- You don't need to load again after training.
4. See it in action! Training will take a while with large dataset!!