🐛 Bug

THe quantize and dequantize currently call into contiguous, which may lead to underlying NHWC=>NCHW change.

To Reproduce

Steps to reproduce the behavior:

1. construct a residual add path, one is from qconv and another is directly from quantize input.

Expected behavior

Environment

Please copy and paste the output from our
environment collection script
(or fill out the checklist below manually).

You can get the script and run it with:

wget https://raw.githubusercontent.com/pytorch/pytorch/master/torch/utils/collect_env.py
# For security purposes, please check the contents of collect_env.py before running it.
python collect_env.py

• PyTorch Version (e.g., 1.0):
• OS (e.g., Linux):
• How you installed PyTorch (conda, pip, source):
• Build command you used (if compiling from source):
• Python version:
• CUDA/cuDNN version:
• GPU models and configuration:
• Any other relevant information:

Additional context

cc @jerryzh168 @jianyuh @dzhulgakov @raghuramank100 @jamesr66a @vkuzo