Skip to content

Latest commit

 

History

History
23 lines (13 loc) · 1.13 KB

README.md

File metadata and controls

23 lines (13 loc) · 1.13 KB

VQ-VAE Keras Implementation

Keras implementaion of VQ-VAE (Vector Quantizer Variational AutoEncoder)

Sources:

Example Notebook: Open In Colab

Original vs Reconstructed

alt text

Notes on compatibility

  • The notebook was created on a Google Colab machine (GPU accelerated) which ran TensorFlow version 1.x

  • The notebook was tested with TensorFlow version 2.2.0 and Keras version 2.3.1 on a Google Colab machine (GPU accelerated) and worked when removing the parameter validate_indices from the call tf.nn.embedding_lookup (it is a deprecated argument).

  • If you have issues with eager execution with TensorFlow version 2.x or higher, issue #2 might help you.