iejMac
iejMac
@TheShadow29 I made a PR with a wrapper that might work for you - https://github.com/iejMac/video2numpy/pull/18 You can test it out on branch ```pt_dl```. A simple example that should work: ```...
@jpfeil will do! Ok I think I'm mostly set up (had to port this code to a repo with a different style). My first question is - do we have...
Oh I also noticed one thing - is there a reason we don't normalize the pixels before passing it into the model? Or did I just not catch where that's...
@lucidrains ah yeah ToTensor does but your VideoDataset doesn't do that and thats what I was using to test (was getting loss ~O(1e5)). https://github.com/lucidrains/magvit2-pytorch/blob/b2f105b9a398264c523c2088f20b7b468200ab78/magvit2_pytorch/data.py#L159
Yes I'm using LFQ from that. The main question I have about config is like can we figure out a parametrization of VideoTokenizer (given all params you added) that corresponds...
cool, was just wondering if you have something on hand. I'll try to read/play around and I'll report here if I come up with something. Also for lowish-effort video dataloading...
openai can you check this out?
openai can you summarize this PR?
openai can you summarize this PR?
@younesbelkada hey, thanks for this! So I understand you want to add support for another *type* of model but keep functionality the same correct? Do you think you could show...