Can QKeras support Full integer quantization

I know I can get the weight and bias to INT8 by setting:
kernel_quantizer=quantized_bits(bits=8, integer=7, alpha=1)
bias_quantizer=quantized_bits(bits=8, integer=7, alpha=1)

However, sometimes, the input tensor is still float because we have to normalize the input.
So, my question is "Can QKeras support the quantization of input tensor?"

Start by reviewing QKeras's existing weight and bias quantizer configuration and how normalized input tensors enter the model. Clarify the intended full-integer behavior and define done as documented support for quantizing the input tensor without losing the required normalization behavior.

Written by the indexing model from the issue text.