[DynamicQuant] Questions about pretrained weight + Some inconsistency

[jyeah05]

Hello,

I found your CVPR paper to be a very interesting study.
I'm currently trying to reproduce your work using your repository, and I would be grateful if you could give me some advice.

I have a question about the first and last layers in ResNet.
It seems like the code uses full-precision (FP) for both layers, but don't they need to be quantized to 8 bits?

Secondly, I was wondering whether FP pretrained weights are used for DQnet training or if DQnet is trained from scratch without using any pretrained weights.

Thank you for your time and assistance!

[liu-zhenhua]

1. The full-precision is used for the first and last layers, you can also quantize them to 8 bits, which will only decrease the performance as verified in the previous works.
2. The pretrained weights are used for DQNet training.