sunshineatnoon / paper-implementations Goto Github PK

I tried backward errD((errD_fake + errD_real)*0.5) and original code only backward total generator loss, but in this code, the result worse than separate backward errD_fake and errD_real.

the output size of the convolutional layer is not 30*30?
Meanwhile, there shouldn't be a sigmoid layer at the end?
https://github.com/sunshineatnoon/Paper-Implementations/blob/master/cycleGAN/model/Discriminator.py

I am talking about vgg in
vgg.py

The model is inconsistent with pre-trained model provided torchvision package

from torchvision.models import vgg16

The pre-trained model in torchvision package as follow:

VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace=True)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace=True)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace=True)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace=True)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace=True)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace=True)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace=True)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace=True)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace=True)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace=True)
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

As you see, the model does not contain layer conv3_4, conv4_4, and conv5_4.

When I changed the input_nc and output_nc with 1,it came out such problem:

Traceback (most recent call last):

File "CycleGAN.py", line 209, in
outA = D_A(real_A)
File "/home/ccc/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/ccc/cchoi/Paper-Implementations/cycleGAN/model/Discriminator.py", line 56, in forward
out = self.layer1(x)
File "/home/ccc/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/ccc/anaconda2/lib/python2.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/ccc/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/ccc/anaconda2/lib/python2.7/site-packages/torch/nn/modules/conv.py", line 301, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight[64, 1, 4, 4], so expected input[1, 3, 512, 512] to have 1 channels, but got 3 channels instead
Exception NameError: "global name 'FileNotFoundError' is not defined" in <bound method _DataLoaderIter.del of <torch.utils.data.dataloader._DataLoaderIter object at 0x2ac957b05d50>> ignored
Exception NameError: "global name 'FileNotFoundError' is not defined" in <bound method _DataLoaderIter.del of <torch.utils.data.dataloader._DataLoaderIter object at 0x2ac957b33550>> ignored

How could I train the dataset with just 1channel?

In script NeuralSytleTransfer/train.py

the open_and_resize function should not hard-code

styleImg = transform(util.open_and_resize_image(opt.style_image,256))
contentImg = transform(util.open_and_resize_image(opt.content_image,256))

rather, it should use parameters from opt.imageSize

In the cycle gan code i am getting the following error while training the model

File "CycleGAN.py", line 211, in
outA = D_A(real_A)
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/media/iab/New Volume/soumyadeep/Paper-Implementations-master/cycleGAN/model/Discriminator.py", line 57, in forward
out = self.layer2(out)
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/nn/modules/container.py", line 67, in forward
input = module(input)
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/media/iab/New Volume/soumyadeep/Paper-Implementations-master/cycleGAN/model/Discriminator.py", line 25, in forward
mean = torch.mean(t, 2).unsqueeze(2).expand_as(x)
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/autograd/variable.py", line 725, in expand_as
return Expand.apply(self, (tensor.size(),))
File "/home/iab/anaconda2/envs/pytorch/lib/python2.7/site-packages/torch/autograd/_functions/tensor.py", line 111, in forward
result = i.expand(*new_size)
RuntimeError: The expanded size of the tensor (32) must match the existing size (128) at non-singleton dimension 2. at /opt/conda/conda-bld/pytorch_1503966894950/work/torch/lib/THC/generic/THCTensor.c:323

PLEASE HELP !!

我试过按照代码中errD_fake和errD_real分别backward，D网络和G网络以及L1的loss都能下降，用errD去backward，errD_real迅速降到零，errD_fake一直在上升，这是为什么呢