ZeroQ

ZeroQ copied to clipboard

Why do the weights need to be dequantized after one quantization?

1

new_quant_x = linear_quantize(x, scale, zero_point, inplace=False) n = 2**(k - 1) new_quant_x = torch.clamp(new_quant_x, -n, n - 1) quant_x = linear_dequantize(new_quant_x, scale, zero_point, inplace=False) Doesn't this get the weight of...

lotusdaddy

The accuracy of pytorch official model is 0.3% lower than full precision

1

I've used the pytorch official resnet50 (https://pytorch.org/docs/stable/torchvision/models.html) in your ZeroQ, and it only gives 75.85 (full precision is 76.13) All I do is change the model loading line in uniform_test.py...

talenz

生成数据时，提取的网络激活位置是否有bug?

1

感谢您的杰出工作，有一个小问题想问下： 在distill_data.py中：  87行代码，hook提取到的特征都是卷积后的值，但这种做法是不是默认了卷积后一定是BN？ 如果一个网络存在某些conv后没有加BN，那么此时计算论文中公式3，可能是“不同层的两个BN参数间的计算” 感谢~

Fangkang515

When I use ImageNet Val dataset to calibrate 4bit resnet18, I got a result of 8.77%, while the distilled data could reach 20%. So original data is not perfect to...

ThisisBillhe

yykhuster

Just observed that the backpropagation part for the quantized model has not been implemented yet in the quant_utils.py file. Any ideas on how to approach the implementation?

karthikramesh55

Quantize tensor is not enough

4

Great job, you give the best quantization accuracy as I know. I'm very interested in your paper and code, but I have some issue about this paper. As far as...

dreambear1234

Hi, I have a question for training the quantized SSD detector. It seems there is no script to run training. How can I train the quantized detector using this framework?...

LiYunJamesPhD

How to export the quantized model into pth file?

thuyngch

bitwidth of each layer (discussion of MP)

2

Thanks for your great works. I want to know which layers are more sensitive to quantization. I would be very grateful if you can share the (MP4) bit-width of each...

hustzxd