https://github.com/sayakpaul/keras-convnext-conversion

ConvNeXt conversion code for PT to TF along with evaluation code on ImageNet-1k val.
https://github.com/sayakpaul/keras-convnext-conversion

cnns convnext deep-learning image-recognition keras

Last synced: 14 days ago
JSON representation

ConvNeXt conversion code for PT to TF along with evaluation code on ImageNet-1k val.

• Host: GitHub
• URL: https://github.com/sayakpaul/keras-convnext-conversion
• Owner: sayakpaul
• License: apache-2.0
• Created: 2022-04-17T06:06:32.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2022-05-12T03:41:56.000Z (over 2 years ago)
• Last Synced: 2024-10-10T17:30:48.541Z (27 days ago)
• Topics: cnns, convnext, deep-learning, image-recognition, keras
• Language: Python
• Homepage: https://www.tensorflow.org/api_docs/python/tf/keras/applications/convnext
• Size: 82 KB
• Stars: 10
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
This repository holds the code that was used to populate the official ConvNeXt

parameters [1, 2] into Keras ConvNeXt implementation. Most of the code is copied

from here: https://github.com/sayakpaul/ConvNeXt-TF. Please refer to this repository

for more comments, setup guides, etc. 

The conversion was performed to aid this PR: https://github.com/keras-team/keras/pull/16421.

**Updates**

* The above-mentioned PR's been merged and that means it's now available inside TensorFlow

(nightly) for now. Here's the official documentation: https://www.tensorflow.org/api_docs/python/tf/keras/applications/convnext.

* Transfer learning code reference can be found [here](https://keras.io/guides/transfer_learning/).

## Execution

1. Install the Python dependencies: `pip install -r requirements.txt`.

2. Make sure you're at the root of the repository after cloning it.

3. Then create the required directories:

  ```sh

  $ mkdir keras-applications

  $ mkdir keras-applications/convnext

  ```

4. Then execute: `python convert_all.py`.

## References

[1] ConvNeXt paper: https://arxiv.org/abs/2201.03545

[2] Official ConvNeXt code: https://github.com/facebookresearch/ConvNeXt