Summary: This post showcases a workaround to optimize a tf.keras.Model model with a TensorFlow-based L-BFGS optimizer from TensorFlow Probability. The complete code can be found…

# Tag: Python

I wrote this blog post to remind myself of something. When evaluating the order of convergence of numerical simulation results, we either use infinity norm…

Note: The content in this post was done with the GPU version of TensorFlow 2.0. I needĀ float64 for my models. However, not until recently I…

Disclaimer: I use the Keras interface from TensorFlow 2.0.0-rc1, so I’m not sure if the content applies to the original Keras library or other versions…

Disclaimer: I only use the GPU version of TensorFlow v2.0.0-rc1, so I don’t know if this works with other versions. When writing the TensorFlow code…