Add EfficientNet lite option [from tensorflow closed PR]

[davinnovation]

System information.

TensorFlow version (you are using): 2.9.1 Are you willing to contribute it (Yes/No) : No

Describe the feature and the current behavior/state.

Add EfficientNet Lite option which is PRed in [Added Lite option to EfficientNets. #48400] https://github.com/tensorflow/tensorflow/pull/48400/ already

Will this change the current api? How? Yes. tf.keras.applications.efficientnet.EfficientNetB0(lite=True)

Who will benefit from this feature?

• EfficientNet Lite Users

Contributing

• Do you want to contribute a PR? (yes/no): no
• If yes, please read this page for instructions
• Briefly describe your candidate solution(if contributing):

[tilakrayal]

@davinnovation, Could you please elaborate about your Feature. Also, please specify the Use Cases for this feature. Thank you!

[davinnovation]

Hi! Thanks for your response. For clearance, efficientnet lite PR is not my credit - it was PRed by @sebastian-sz to the TensorFlow repo in 2021 Q3. This feature is adding "lite:bool" parameter to tf.keras.applications.efficientnet.EfficientNet and it makes loadable TF2-TFlite ready efficientnet-lite keras model.

EfficientNet lite is in TF-Hub, but it is for TF1 so it can't be easily ported with TF2-TFLite

If this feature is added, lots of users can easily port efficient-lite with the latest TF2-TFLite

[sebastian-sz]

@davinnovation Hi, sorry for not reopening the PR in Keras repository as promised.

If it will be accepted I am planning to add these models to keras-cv - I think this is the target place to add new vision keras.applications.

[gadagashwini]

Hi @sebastian-sz, It would be great if you raise PR in this repo. Thank you!

[sebastian-sz]

@gadagashwini in "this" repo, do you mean keras-cv or keras?

[google-ml-butler[bot]]

This issue has been automatically marked as stale because it has no recent activity. It will be closed if no further activity occurs. Thank you.

[google-ml-butler[bot]]

Closing as stale. Please reopen if you'd like to work on this further.

[gadagashwini]

Hi @sebastian-sz, Apologies for delayed response. Please raise PR on Keras repo. Thank you!

[sebastian-sz]

@gadagashwini thanks, I will try to have a PR ready by the end of the week.