wfs123456/CCTrans

Pretrained weights for small and base

Closed this issue · 8 comments

arthuremir commented

Hi! Thanks for the awesome work!

Can you please share the pretrained weights for small and base models? Or, if you don't have them, maybe you can share the code for pretraining? It would be very helpful for me!

Thank you in advance!

wfs123456 commented
arthuremir commented

Ah, thanks!

arthuremir commented

Hi!

Did you test small and base models? Seems like it fails with a shape mismatch at any input sizes.
Code snippet:


model = ALTGVT.alt_gvt_base(pretrained=False)

model.eval()

for img_size in range(50, 1500):
    inputs = torch.randn((1, 3, img_size, img_size))
    try:
        model(inputs)
        print('works fine', img_size)
    except:
        print('failed on', img_size)
wfs123456 commented
arthuremir commented

Sorry, my first question is not directly related to second. (May be I should create another issue)

I'm trying to run small and base models from CCTrans (even without preloaded weights) and getting a shape mismatch. Large models successfully processes input sizes 256, 512, and 768, but small and base models fail on all of them. So may be there are some architecture issues?

wfs123456 commented
arthuremir commented

Do you mean that the small and base models should work correctly on the input with shape (1, 3, 224, 224)?

arthuremir commented

I'm asking because small and base models give shape mismatch on (1, 3, 224, 224).