Add squeeze / unsqueeze operations to quant invariant functions in torch_handler.py

[nickfraser]

No description provided.

[sanjay-rb]

Hi @nickfraser ,

You wanted to add squeeze / unsqueeze operations in quant_invariant_handler function right ?

[Giuseppe5]

When dealing with squeeze/unsqueeze, we also have to handle the shapes of scale factors and zero points.

Related to #728

[ScXfjiang]

For per-channel quantization

Squeeze/Unsqueeze OP is more like Permute OP, where we can find easy ways to modify the QuantTensor to keep those OPs affine quantization invariant. In the case of Squeeze/Unsqueeze OP, all we need to do is squeeze/unsqueeze the scale and zero point tensor accordingly.

However, OPs mentioned in #728 (reshape, flatten) are non-trivial. There are no trivial ways to modify the QuantTensor to keep those OPs affine quantization invariant. Recalculation of scale and zero point is inevitable. We may need to dequantize --> reshape/flatten --> requantize to bypass this problem, at the price of precision loss.

It looks like PyTorch doesn't solve this problem either. They don’t offer a quantized version of the flatten(); instead, they simply use torch.flatten(). QUANTIZATION API REFERENCE

[ScXfjiang]

Hi @nickfraser @Giuseppe5,

A PR has been submitted to solve this issue. Your comments are highly appreciated, many thanks.

#941