We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hi gents,
I wanna support your SynthClip as part of open_clip. Similar to what we did in #6 .
Could you please take a look at this on your end? I'm struggling again 😖 . The output of the synthclip_openclip.py is:
synthclip_openclip.py
Compose( Resize(size=224, interpolation=bilinear, max_size=None, antialias=True) CenterCrop(size=(224, 224)) Lambda() ToTensor() Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) )= Model setup 🎉 Load & preprocess image... Fwd-pass model... Label probs: tensor([[0.0755, 0.3281, 0.5965]], device='cuda:0')
while the expected output should be Label probs: tensor([[0.0048, 0.0878, 0.9075]], device='cuda:0')
Label probs: tensor([[0.0048, 0.0878, 0.9075]], device='cuda:0')
cc @HaniItani
The text was updated successfully, but these errors were encountered:
I'd advise to install open_clip via
cd open_clip # open_clip setup steps pip install -e . # copy the misc stuff in the gist :wink:
Sorry, something went wrong.
No branches or pull requests
Hi gents,
I wanna support your SynthClip as part of open_clip. Similar to what we did in #6 .
Could you please take a look at this on your end?
I'm struggling again 😖 . The output of the
synthclip_openclip.py
is:while the expected output should be
Label probs: tensor([[0.0048, 0.0878, 0.9075]], device='cuda:0')
cc @HaniItani
The text was updated successfully, but these errors were encountered: