Skip to content

Conversation

pkgoogle
Copy link
Collaborator

@pkgoogle pkgoogle commented Oct 17, 2024

Ports efficientnet_b0_ra_imagenet and efficientnet_b1_ft_imagenet presets to EfficientNet and creates the scaffolding for further work

Tested Colab

@divyashreepathihalli divyashreepathihalli added the kokoro:force-run Runs Tests on GPU label Oct 18, 2024
@kokoro-team kokoro-team removed the kokoro:force-run Runs Tests on GPU label Oct 18, 2024
Copy link
Collaborator

@divyashreepathihalli divyashreepathihalli left a comment

Choose a reason for hiding this comment

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

Thanks @pkgoogle. Left a few NIT comments

expand_ratio=stackwise_expansion_ratios[i],
se_ratio=squeeze_and_excite_ratio,
activation=activation,
project_activation=project_activation,
Copy link
Collaborator

Choose a reason for hiding this comment

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

nit: project->projection

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

done

kernel_size=3,
strides=1,
activation="swish",
project_activation=None,
Copy link
Collaborator

Choose a reason for hiding this comment

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

project->projection

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

done

depthwise_initializer=conv_kernel_initializer(),
name=name + "dwconv",
)(x)

Copy link
Collaborator

Choose a reason for hiding this comment

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

remove blank line

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

done

@@ -0,0 +1,226 @@
import math
Copy link
Collaborator

Choose a reason for hiding this comment

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

add instructions on how to run the checkpoint conversion script. see resnet script for example
"""
python ....
"""

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Did you mean this? The analogous convert_resnet.py does not have examples: convert_resnet.py

"metadata": {
"description": (
"EfficientNet B0 model pre-trained on the ImageNet 1k dataset "
"with RandAugment recipe."
Copy link
Collaborator

Choose a reason for hiding this comment

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

what is the random augment recipie?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Here's the paper... should we link it?

@divyashreepathihalli divyashreepathihalli added the kokoro:force-run Runs Tests on GPU label Oct 28, 2024
@kokoro-team kokoro-team removed the kokoro:force-run Runs Tests on GPU label Oct 28, 2024
@divyashreepathihalli divyashreepathihalli merged commit 36cc11a into keras-team:master Oct 29, 2024
10 checks passed
@pkgoogle pkgoogle deleted the finish_efficient_net branch October 29, 2024 17:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants