Input and resource quantization

[Jwy-Leo]

System information

• TensorFlow version (you are using): tensorflow 2.9.1
• Are you willing to contribute it (Yes/No): No

Motivation The input and resource need interface for customer layer quantization, Normalization is a basic structure in the DNN, but we cannot quantize it easily.

1. No input quantization interface in customer configuration, it will make quantization mul-add structure in float32 instead of int8 in tflite file.
2. No resource quantization interface in customer configuration, it will make batchnorm - (running mean, running variance) wo/ QAT.

[Xhark]

Hi, would you please give us some examples? We usually assume BNs would be folded (fused) to nearby layer for optimization. I'd like to know some use-cases that when it required. Thanks.