Laurent/REVA-QCAV
1
0
Fork 0
mirror of https://github.com/Laurent2916/REVA-QCAV.git synced 2024-11-08 14:39:00 +00:00
Code Issues Packages Projects Releases Wiki Activity
10 commits 1 branch 0 tags 38 MiB
Python 100%
Find a file
milesial e1bf150da3 Updated README.md 
Former-commit-id: 03065569518394e7b686e6995d05599f9822417f
2017-11-30 03:44:29 +01:00
.gitignore Created a basic train loop + changed a bit loss and utils 2017-08-17 21:16:19 +02:00
crf.py Added simple predict + submit script 2017-08-21 18:00:07 +02:00
data_vis.py Created a basic train loop + changed a bit loss and utils 2017-08-17 21:16:19 +02:00
eval.py Added simple predict + submit script 2017-08-21 18:00:07 +02:00
load.py Added simple predict + submit script 2017-08-21 18:00:07 +02:00
main.py Added simple eval and test CRF 2017-08-19 10:59:51 +02:00
MODEL.pth.REMOVED.git-id Added simple trained model 2017-08-23 17:38:55 +02:00
myloss.py Created a basic train loop + changed a bit loss and utils 2017-08-17 21:16:19 +02:00
predict.py Added simple predict + submit script 2017-08-21 18:00:07 +02:00
README.md Updated README.md 2017-11-30 03:44:29 +01:00
submit.py Final tweaks 2017-09-26 21:00:51 +02:00
train.py Added simple trained model 2017-08-23 17:38:55 +02:00
unet_model.py Created a basic train loop + changed a bit loss and utils 2017-08-17 21:16:19 +02:00
unet_parts.py Added simple eval and test CRF 2017-08-19 10:59:51 +02:00
utils.py Final tweaks 2017-09-26 21:00:51 +02:00

README.md

Pytorch-UNet

Customized implementation of the U-Net in Pytorch for Kaggle's Carvana Image Masking Challenge.

This model scored a dice coefficient of 0.988423 (511 out of 735), which is bad but could be improved with more training, data augmentation, fine tuning, and playing with CRF post-processing.

The model used for the last submission is stored in the MODEL.pth file, if you wish to play with it. The data is available on the Kaggle website.

Note

The code and the overall project architecture is a big mess for now, as I left it abandoned when the challenge finished. I will clean it SoonTM.