Closed lenwen-hub closed 1 year ago
/home/lenwen/PRO_mine/PycharmPRO/UNET/Image_Segmentation-master/venv/bin/python /home/lenwen/PRO_mine/PycharmPRO/UNET/Image_Segmentation-master/main.py
Namespace(augmentation_prob=0.43997968647369484, batch_size=1, beta1=0.5, beta2=0.999, cuda_idx=1, image_size=224, img_ch=3, log_step=2, lr=0.00027232275207867595, mode='train', model_path='./models', model_type='U_Net', num_epochs=250, num_epochs_decay=22, num_workers=8, output_ch=1, result_path='./result/U_Net', t=3, test_path='./dataset/test/', train_path='./dataset/train/', val_step=2, valid_path='./dataset/valid/')
image count in train path :6000
image count in valid path :2000
image count in test path :2000
/home/lenwen/.local/lib/python3.6/site-packages/torch/nn/functional.py:1625: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.
warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.")
/home/lenwen/.local/lib/python3.6/site-packages/torch/nn/modules/loss.py:529: UserWarning: Using a target size (torch.Size([1, 196608])) that is different to the input size (torch.Size([1, 65536])) is deprecated. Please ensure they have the same size.
return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
Traceback (most recent call last):
File "/home/lenwen/PRO_mine/PycharmPRO/UNET/Image_Segmentation-master/main.py", line 101, in
Process finished with exit code 1
196608 = 65536 * 3 the value of output_ch is 1, so the channel of GT png should be 1 , not 3
I also have this problem. Have you solved this problem yet? If yes, can you tell me how to solve it? Thanks.
![Uploading 2020-09-28 19-21-19 的屏幕截图.png…]()