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
How to modify pre-trained models? #23
Comments
Hi. There are many ways. The easiest and dirtiest one is an instance method replacement (see a discussion). Example (for PyTorch):
|
That seems to work well, thanks! |
First of all, if you modify only
|
Great, thanks for the help! |
Hey, sorry to re-open this - I've got a related question if that's okay? I'm trying to run my model on multiple gpus with the modified forward function as above, but keep getting the following error :
|
Hi, This is a very good question for the https://discuss.pytorch.org/. |
Great, I'll post there. Thanks! |
Is there a good way to go about modifying the pre-trained models? I want to tweak the forward() function to return activations at a few layers.
I'm going to be comparing between several CIFAR models so training them all myself isn't really viable.
Thanks!
The text was updated successfully, but these errors were encountered: