style_transfer
style_transfer copied to clipboard
Data-parallel image stylization using Caffe.
Hello, I am writing a GUI for style-transfer, and one option is a mystery to me : of what use is the auxiliary image ? I have tested a little,...
great project, here is a colab port i put together: https://colab.research.google.com/drive/1_ECeeuQPeTQ_51FTgeymfsFotLemIRQM
I successfully compiled NVCaffe, however I'm getting this error when I run style_transfer.py: Run 190122_141358 started. Initializing vgg19.caffemodel. Watch the progress at: http://127.0.0.1:8000/ Starting 1 worker process(es). ======== Running on...
Seem to have run into a bug where the loss exploded. See below, step 337: Using Ubuntu 16.04, Python3.6, CUDNN6.1, CUDA8.0, MKL, GPU. > Parameters: > aux_image: None > aux_weight:...
The style_transfer AMI does not seem to have been updated with the wavelet denoising feature. Running "git pull" seems to break style_transfer. The AMI: https://github.com/crowsonkb/style_transfer/wiki/Cloud-computing-images Error when running "git pull::...
Please explain how to compile it on Windows. I found Makefile.config in docker folder, edited the paths in that file. And ... what next? Where should I copy that file?...
I'm not able to replicate (something close) neural-style (https://github.com/jcjohnson/neural-style) results in the generated art. Using single-scale and turning off some of the extra features. Is there something I'm missing or...
Is there a way to use the original image color in the output? Similar to neural style's OriginalColor parameter?
On any kind of error it seems the script doesn't stop itself, it still requires ctrl+c to return to the command line. This isn't a big deal if it hasn't...
Both [NeuralImageSynthesis](https://github.com/leongatys/NeuralImageSynthesis), and [deep-photo-styletransfer](https://github.com/luanfujun/deep-photo-styletransfer) support masked style transfer, where one uses mask images as guides. The latter supports mask images with multiple colors instead of the traditional black and white...