Delighted to present a comprehensive inference benchmark around the vision models shipped in the Keras ecosystem (tf.keras.applications
, TF Hub, and KerasCV).
- Code: GitHub - sayakpaul/keras-xla-benchmarks: Presents comprehensive benchmarks of XLA-compatible pre-trained models in Keras.
- Report (with Soumik Rakshit and @ayush_thakur): Weights & Biases
I hope it provides you with some interesting insights.