Replies: 1 comment
-
@tms2003 it's fully convolutional, don't need to pass any parameter related to image size at creation time, just give it a larger image size when you use it. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I want to use a custom input image width and height, such as 640X640. How can I modify the model parameters such as convnext in timm create_model?
Beta Was this translation helpful? Give feedback.
All reactions