Object-Detection-Knowledge-Distillation

Object-Detection-Knowledge-Distillation copied to clipboard

zhaoqian11

Hello, Can you please explain how these values were computed? MEANS = (127, 127, 127) I tried to compute them by myself on the VOC2007+2012 dataset, and I obtained these...

EdenBelouadah

with different dataset

3

can I use different dataset instead of VOC，please ？

ljn1060532268

The given teacher checkpoint (vgg) doesn't fit with the current version of VGG in the repo.

2

``` size mismatch for loc.0.weight: copying a param with shape torch.Size([16, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 1024, 3, 3]). size mismatch for loc.1.weight:...

TheLostIn

Hello, Firstly, thank you very much for this great repository. I am really interested to run your code on a video, where the teacher transfers his knowledge to the student....

EdenBelouadah

RuntimeError: CUDA error: out of memory

2

Hi, I always got the run time error after I ran python eval.py mbv2 --trained_model=checkpoints/student_mbv2_500_3934.pth. Does anyone know how to solve this error? Thanks.

LiYunJamesPhD

Thanks for the awesome implementation. I had a look at the losses and for the yolov5 implementation: 1. this implementation does not have the teacher bounded regression loss. 2. Also,...

iamsuryan

https://github.com/SsisyphusTao/SSD-Knowledge-Distillation/blob/0597fbee635afcf0b8710ba3a9e40ab9f010aea5/nets/multibox_loss.py#L17-L23 F.mse_loss has reduction='mean' by default, but we should use reduction='sum' as for `loss_l` https://github.com/SsisyphusTao/SSD-Knowledge-Distillation/blob/0597fbee635afcf0b8710ba3a9e40ab9f010aea5/nets/multibox_loss.py#L120 I think the next code corresponds to the formula from the article. ``` def bounded_regression_loss(Rs,...

PalkoNazar

hint loss 不是计算logits的L2距离吧

1

https://github.com/SsisyphusTao/SSD-Knowledge-Distillation/blob/0597fbee635afcf0b8710ba3a9e40ab9f010aea5/nets/multibox_loss.py#L158

forseeking

https://github.com/SsisyphusTao/SSD-Knowledge-Distillation/blob/0597fbee635afcf0b8710ba3a9e40ab9f010aea5/nets/multibox_loss.py#L8

forseeking