search

NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.6k stars 1.2k forks source link

Vid2vid architecture visualization #74

Open mayazshirazi opened 5 years ago

mayazshirazi commented 5 years ago

Hi, I am working on Vid2vid using the data set of RGB videos. I have used the option 'tf_log' for the visualization of the plots for losses and successfully drawn those plots using tensor board. The tensor board based logging is working for plots of losses and generated images, but I am unable to visualize the whole architecture of vid2vid in tensor board. Can you guide me how to modify the visualizer.py file so as to visualize the whole architecture of vid2vid? Kindly share the architecture diagram of the vid2vid if you have one and also provide me any script to visualize the vid2vid architecture.

Thanks

chaitanyabaranwal commented 4 years ago

Not sure if this is relevant to anyone anymore, but the architecture diagram for the vid2vid network can be found in the appendix (at the end) of the research paper!