antialiased-cnns
antialiased-cnns copied to clipboard
adobe
pip install antialiased-cnns to improve stability and accuracy
The code had 2D and 1D blurpooling modules which had a lot of code duplicated. Unified that code and added a similar 3D blurpooling module. ## Motivation and Context Adds...
The filters are made by multiplying against its flipped copy, so it should work fine if it was kept as, for example, 1x7 instead of 7x7. Then conv2d twice with...
If the channel argument is set to None, keep the filter kernel with only one channel and then in the forward pass use PyTorch's .expand() function to match the input's...
### Expected Behaviour ### Actual Behaviour ### Reproduce Scenario (including but not limited to) #### Steps to Reproduce #### Platform and Version #### Sample Code that illustrates the problem ####...
Hello all, I would like to train the model with CIFAR10. But it gives error with blurring kernel size larger than 3: RuntimeError: Padding size should be less than the...
Hi, it's really refreshing to see signal processing principles used in deep networks. I have a question about the upsampling mechanism. After going through the original code and a related...
Awesome work. Take a look at alias-free gan by Nvidia if you haven't already. https://nvlabs.github.io/alias-free-gan/ The filters in this research only reduce alias by smoothing but using a sinc kaiser...
In experiment , ResNet use parameter "pool_only=True" ? This parameter effect accuracy ? I think "pool_only=False" is more make sense ,but "pool_only=True" is default. In main.py , I can't find...
Hello very nice woks ! I do also struggle with spatial shift sensitivity of my 3D CNN and I would like to test your solution. Is someone aware of a...
``` class BlurPool(KL.Layer): """ https://arxiv.org/abs/1904.11486 https://github.com/adobe/antialiased-cnns """ def __init__(self, filt_size=5, stride=2, **kwargs): self.strides = (stride,stride) self.filt_size = filt_size self.padding = ( (int(1.*(filt_size-1)/2), int(np.ceil(1.*(filt_size-1)/2)) ), (int(1.*(filt_size-1)/2), int(np.ceil(1.*(filt_size-1)/2)) ) ) if(self.filt_size==1): self.a...
