ZeroQ

ZeroQ copied to clipboard

I hava just reproduced the classification on resnet50+imagenet. The accuracy is excellent! But there is a significant increase in inference latency for quantized model. Test results on resnet + imagenet...

ZongqiangZhang

Thank you for sharing the great repo. I ran successfully your code under 8-bit options. In the paper, there is an experiment result with mixed-precision (low-bit). How could I run...

leejaymin

How much calibration data is needed?

3

Hi, Thanks for the great work. I am wondering how many calibration data is needed. According to [here](https://github.com/amirgholami/ZeroQ/blob/master/classification/uniform_test.py#L75) and [here](https://github.com/amirgholami/ZeroQ/blob/master/classification/distill_data.py#L56), only 64 calibration images are good to calibrate the model?...

liming312

In many previous works, they show that it's more difficult to do quantization while the batch normalization is fused with convolution due to wider variance of weight range. So, do...

HKLee2040

The same error happens when running with resnet18 as well. Appreciate any suggestions to get this fixed. $ python ./uniform_test.py --dataset cifar10 --model mobilenetv2_w1 ****** Full precision model loaded ******...

yrajas

Model remains float32 type after quantization

1

Hello, thank you for providing the open-source code. I encountered some issues while trying to reproduce. I set up the environment according to your instructions and run the code. However,...

Blinkblade

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin