pytorch-neural-style-transfer
pytorch-neural-style-transfer copied to clipboard
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the imag...
Editing the neural_style_transfer.py and changing the default value for --height or using --height value on the command line produces no end result. The data/output-images folder created is blank. Edited the...
I've run through the codes and was able to generate images by running the model. I realize that the images generated were sort of over exposed. I modified the codes...
Just an FYI, I was playing around with this repo all morning (awesome work!) and was wondering why it was so slow. It turns out that it was using CPU...
I found an explanation of the total variation loss from the [tutorial](https://www.tensorflow.org/tutorials/generative/style_transfer#total_variation_loss) on the official website of TensorFlow. It says that total variation loss is a regularization term that can...
Would it be possible to use this or a similar library to - instead of transferring a style to another image - build an ML model that learns the style...
Using a combination of vgg19 and lbfgs I have found the script to end after only 8 iterations. In addition, when using a different combination (like vgg16 & lbfgs or...
I am having an issue running reconstruct code: `RuntimeError: module compiled against API version 0xe but this version of numpy is 0xd` I ran the `pip install numpy --upgrade` command...
This parameter exists in an [jcjohnson implementation](https://github.com/jcjohnson/neural-style). This basically makes extracted patterns from the style image smaller (or bigger if higher than 100%).
I was running into issues trying to re-create the original paper, and stumbled upon this repository. I was able to re-create the results when using the caffe pretrained model (which...