UniversalStyleTransfer icon indicating copy to clipboard operation
UniversalStyleTransfer copied to clipboard

The source code of NIPS17 'Universal Style Transfer via Feature Transforms'.

Results 11 UniversalStyleTransfer issues
Sort by recently updated
recently updated
newest added

Is there any evaluation script for SSIM metrics?

I see you explained in the paper that the model can achieve multi-style transfer using masks. Is it means that without the masks, the model is not suitable for multi-style...

I use `torch.utils.serialization.load_lua` Python pkg to load the `vgg_normalised_conv5_1.t7`, the net is as followed: ``` In [7]: vgg1 = load_lua('models/vgg_normalised_conv1_1.t7') In [8]: vgg1 Out[8]: nn.Sequential { [input -> (0) ->...

I downloaded [encoders&decoders](https://drive.google.com/file/d/0B8_MZ8a8aoSeWm9HSTdXNE9Eejg/view) and replaced decoders with the these [decoders](https://drive.google.com/file/d/1wVPtu4gGkUWpb9YtRecveFvdo4ZN5kMD/view) (for those not having cuDNN). But actually I have cuDNN7 (cuDNN5 is not supported with my CUDA version 9.1). Then...

Your algorithm was implemented in C# for use on Windows. You can find it here:[https://github.com/ColorfulSoft/Demos/tree/master/Style%20Transfer/2017.%20Universal%20Style%20Transfer%20via%20Feature%20Transforms.](https://github.com/ColorfulSoft/Demos/tree/master/Style%20Transfer/2017.%20Universal%20Style%20Transfer%20via%20Feature%20Transforms).

Thank you for your work. Can you provide the training code? I want to know some training details, such as learning rates, optimization methods and so on.

Hi is there a CPU mode only flag available?

Hey! I've tried running this on a single GPU with 4GB DDR, but I get: ``` cuda runtime error (2) : out of memory at ~/torch/extra/cutorch/lib/THC/generic/THCStorage.cu:66 ``` Before I break...

Hi there is a patchy areas that jump around between images in video transfer. This isnt so much temporal issues with the style transfer of features as much as little...

From my understanding the SVD sigma matrix contains the square root of the eigenvalues of the right and left singular vectors thus performing another square root is not required. I...