Slow training

Hi everyone

Is it expected behavior that the quantization-aware training in QKeras is much slower than normal training in Keras? And if so, out of interest, where does the overhead come from? From the quantization-dequantization operation?

Thank you for your help!

The issue names no files, tests, or entry points. Compare QKeras quantization-aware training with normal Keras training, profile the quantization and dequantization operations, and document whether the slowdown is expected and where the overhead comes from.

Written by the indexing model from the issue text.