Pytorch-UNet
Pytorch-UNet copied to clipboard
milesial
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Hi,I faced a weird problem: At first,my parameters are: epoch:10 bantch-size:1 class:2 and the train.py ran successfully! However,when I increased batch-size from 1 to 2(and 3,I tried),but without changing any...
I directly download the pretrained model by `mask_encoder = torch.hub.load('milesial/Pytorch-UNet', 'unet_carvana', pretrained=True, scale=0.5)` but it seems have some error ``` File "/home/xxx/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/hub.py", line 404, in load model = _load_local(repo_or_dir, model,...
when i run the predict.py , it has some mistakes: Traceback (most recent call last): File "/home/atr2/Code/Pytorch-UNet-master/predict.py", line 101, in img = Image.open(filename) File "/home/atr2/anaconda3/envs/PyTorch/lib/python3.7/site-packages/PIL/Image.py", line 2904, in open fp...
when the epoch 1 run for a time the error was raised: 'ValueError: autodetected range of [nan, nan] is not finite' do u know how to fix this problem?Thanks for...
I used my own dataset to make predictions, the picture size is 200*200 Three-channel and th mask for single channel Only black and white. Trying to adjust the learning rate...
Hi!I trained the model on the ultrasonic grayscale image, since there are only two classes, I changed the code to net = UNet(n_channels=1, n_classes=1, bilinear=True), and when I trained, the...
File "/disk/sdc/shejiao/Pytorch-UNet-master/evaluate.py", line 19, in evaluate mask_true = F.one_hot(mask_true, net.n_classes).permute(0, 3, 1, 2).float() RuntimeError: number of dims don't match in permute
