RepQ-ViT

RepQ-ViT copied to clipboard

reproduced performance is poor in swin-base

1

Hi, I try to reproduce the classification accuracy using this code. They correspond to your paper except for swin-base. I only get 68.50%, and there is a 10% gap with...

XA23i

I am trying to run your code, but I cannot install the packages based on the instructions provided. Can you give the latest instructions for running your code?

harshaUwm163

How to save and load the quantized model?

2

KaidDuong

Discrepancy between reported and tested mAP for `mask_rcnn_swin_small`

3

Hello! In your four detection experiments, I noticed a significant difference between the reported result and the test result for `mask_rcnn_swin_small`. The reported result is 44.2 mAP, but the tested...

GoatWu

AttributeError: 'Attention' object has no attribute 'reduction'

1

When I try to run the code, there is a problem in line 117 of test_quant.py "next_module = father_module.reduction". my shell is "python test_quant.py --model deit_small --dataset /root/data/Imagenet". Is there...

Arthur-Ling

Hello! May I inquire if the LayerNorm module has not been quantized in this model?

3

GoatWu

pengpan6934

为什么将Scale reparameterization注释掉后模型的精度反而上升了很多？

1

pengpan6934