Skip to content
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

load_state_dict does not return the model #1503

Merged
merged 11 commits into from
Feb 6, 2024
Merged

load_state_dict does not return the model #1503

merged 11 commits into from
Feb 6, 2024
+18 −14

Commits on Jan 3, 2024

  1. Update pretrained_weights.ipynb 

    Fixed an error in the state dict loading of the turorial and added a comment on the num_classes parameter when creating timm models.
    @konstantinklemmer @isaaccorley
    konstantinklemmer authored and isaaccorley committed Jan 3, 2024
    Configuration menu
    Copy the full SHA
    7cd3f61 View commit details
    Browse the repository at this point in the history

  2. Update docs/tutorials/pretrained_weights.ipynb

    @calebrob6 @isaaccorley
    calebrob6 authored and isaaccorley committed Jan 3, 2024
    Configuration menu
    Copy the full SHA
    1f976cf View commit details
    Browse the repository at this point in the history

Commits on Jan 30, 2024

  1. Merge branch 'microsoft:main' into patch-1

    @konstantinklemmer
    konstantinklemmer committed Jan 30, 2024
    Configuration menu
    Copy the full SHA
    46a8756 View commit details
    Browse the repository at this point in the history

  2. Update utils.py 

    * Import Tuple from typing
* Change return of `load_state_dict` from `model` to `Tuple[List[str], List[str]]`, matching the return of the standard PyTorch builtin function.
    @konstantinklemmer
    konstantinklemmer committed Jan 30, 2024
    Configuration menu
    Copy the full SHA
    392b305 View commit details
    Browse the repository at this point in the history

  3. Update pretrained_weights.ipynb 

    Remove example of loading pretrained model without prediction head (`num_classes=0`).
    @konstantinklemmer
    konstantinklemmer committed Jan 30, 2024
    Configuration menu
    Copy the full SHA
    46afcd7 View commit details
    Browse the repository at this point in the history

  4. Update README.md 

    Adapt new `load_state_dict` function.
    @konstantinklemmer
    konstantinklemmer committed Jan 30, 2024
    Configuration menu
    Copy the full SHA
    2324488 View commit details
    Browse the repository at this point in the history

Commits on Jan 31, 2024

  1. Mimic return type of builtin load_state_dict

    @adamjstewart
    adamjstewart committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    53885dc View commit details
    Browse the repository at this point in the history

  2. Modern type hints

    @adamjstewart
    adamjstewart committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    fd19ab1 View commit details
    Browse the repository at this point in the history

  3. Blacken

    @adamjstewart
    adamjstewart committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    35b914c View commit details
    Browse the repository at this point in the history

  4. Try being explicit

    @adamjstewart
    adamjstewart committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    b5a9007 View commit details
    Browse the repository at this point in the history

Commits on Feb 5, 2024

  1. Merge branch 'main' into patch-1

    @konstantinklemmer
    konstantinklemmer committed Feb 5, 2024
    Configuration menu
    Copy the full SHA
    f952bab View commit details
    Browse the repository at this point in the history