Unet Review
Name | |
---|---|
Tim Chen | tim20136202@gmail.com |
CT segmentation snapshots
📝 What I have learn
1. Unet for biological images segmentation ...
2. nn.BCEWithLogitsLoss, nn.ConvTranspose2d, nn.BatchNorm2d ...
Environment
1. If out of memory happen,
minimize the batch_size
torch.no_grad() at the error line
Train
python main.py train
Test
load the last saved weight
python main.py test --ckpt=weights_19.pth