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.

Sign up for GitHub

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

Jump to bottom

Implement saving to Torchscript in the pytorch model #18

Open

jatkinson1000 opened this issue Feb 26, 2024 · 0 comments

Assignees

Labels

Member

jatkinson1000 commented Feb 26, 2024

In order to couple to FTorch we need to save the model as a Torchscript file/representation.

This could be done in a separate script, or as a method of the NN model, but ideally by using the tool provided in FTorch.

To do this we need the final model (at least the architecture if not the trained weights) so will discuss this with @yqsun91.

Examples, and a tool to save models can be found in https://github.com/Cambridge-ICCS/FTorch

jatkinson1000 added the Python-repo label

surbhigoel77 self-assigned this

omarjamil self-assigned this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment