New answers tagged


It depends on your application. In case of text recognition, non-uniform kernels are used since the information about text is less on the horizontal axis and more on the vertical axis. If in your case it is applicable then, it will be good idea. But, if it is not you are better off using a smaller uniform kernel (2x2, maybe). You can also zero-pad your image ...


You can denoise a certain fraction of images (preferably 0.25-0.3) randomly for each epoch. Adding Gaussian noise to images gives better results.Refer this : Link


So for neural style transfer, using the particular method described in Gatys paper, nobody has done better than using VGG net. This is seemingly due to VGGs inherent stability and inability to learn non-robust features of images. More on this here: That being said, GANs have had huge success ...

Top 50 recent answers are included