New issue
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
Implementation of convolutional projection #1
Comments
@leoxiaobin oh my bad I just reuse my older SepCon2d class in this repo, I will update that class. |
Done, do let me know if you find any other vulnerabilities in code. |
@leoxiaobin Hi! When will the official implementation be open source? |
@leoxiaobin |
hi, @youngwanLEE, you can get the pre-trained model at https://github.com/microsoft/CvT |
Please find it at https://github.com/microsoft/CvT |
Thanks @leoxiaobin I am adding repo on ReadMe. |
hi, @rishikksh20
Thank you for your quick implementation!
I notice that your depth-wise separable convolution is implemented as depth-wise conv --> point-wise conv. In the paper, CvT's depth-wise seprable convolution is implemented as depth-wise conv --> bn --> point-wise conv.
The text was updated successfully, but these errors were encountered: