Trouble_in

About the batchnorm in CoordAttention

1

Hello, Thank you for your excellent job about the attention. I am a little puzzled about the code. compared to the Senet, there is a batchnorm operation in the CoordAttention....

'ResNetCustom' object has no attribute '_norm_layer'

2

Thank you for your excellent job about the dropblock. However, there are some errors when I run the code. It occured in the 34 line of resnet-cifar10.py, self.layer1 = self._make_layer(block,...

Thank you for your excellent job about the style-transfer. I am a little puzzled about the transformer block of this paper which is different from the code. Why doesn't adopt...

hello, I am very instrested in you excellent job about the style transfer of ECCV2018. but I am puzzled about the hyperparameter of the other style datasets such as gauguin,...

Thank you for your excellent job. when I run the test.py with the csv file ,it seems wrong in the following line: "gt = test_df[test_df[0] == img].to_numpy()[:, 1:].reshape(10, 1)", some...

So sorry to bother you . I have a little bit of trouble calculating the log(Ls) of various methods in Table 2. The logarithm of the loss with covariance matrix...

About the skip-connection

2

Thank you for your excellent job about the haze removal task. Why don't use the skip-connection between the input hazy image and the output image? I am a little puzzled...

class VGGLoss(nn.Module): def __init__(self, gpu_ids): super(VGGLoss, self).__init__() self.vgg = Vgg19().cuda() self.criterion = nn.L1Loss() self.weights = [1.0/32, 1.0/16, 1.0/8, 1.0/4, 1.0] So sorry to bother you. However, I am puzzled about...

Thanks a lot for this project.

about the mat file

2

Good evening, Given a video, how to prepare the mat file that can be used in this project?