Skip to content
This repository was archived by the owner on Oct 13, 2021. It is now read-only.

Better conversion for the subclassing model and code reformat. #446

Merged
merged 5 commits into from
Apr 18, 2020

Conversation

wenbingl
Copy link
Member

No description provided.

@wenbingl wenbingl requested a review from jiafatom April 17, 2020 19:08
"from skimage.io import imread\n",
"model = efn.EfficientNetB7(weights='imagenet')"
"model = efn.EfficientNetB0(weights='imagenet')"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not using EfficientNetB7?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

too slow for user trying B7 end to end. Given it's a tutorial, it should be simple and fast.

import traceback
tb = traceback.format_exc()
k2o_logger().warning(tb)
if not topology.debug_mode:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

topology.debug_mode will skip optimization?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, the optimization makes the final model to be hard for debugging.

@wenbingl wenbingl merged commit 9316ad6 into onnx:master Apr 18, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants