I want to make sure that the file mv2-r50.pth in the detection pretrained weights you provided contains both teacher's and student's weights.

Thank you!

Hi Author, thanks for your excellent work. I want to ask whether you can release a log file that includes loss values. Based on this file, I can check what‘s the loss change? It is better for the detection model. It would be the best for retinanet. Thank you!

When I run your scripts "reviewKD.sh" and "baseline.sh" in Cifar100. There's FileNotFoundError:

FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/cifar100_wrn-40-2__baseline1_best.pt'
Namespace(T=4.0, batch_size=128, ce_loss_weight=1.0, dataset='cifar100', epochs=240, gamma=0.1, kd_loss_weight=5.0, kd_warm_up=20.0, kl_loss_weight=1.0, lr=0.1, lr_adjust_step=[150, 180, 210], model='wrn-40-1', resume='', seed=148, suffix='reviewkd1', teacher='wrn-40-2', teacher_weight='checkpoints/cifar100_wrn-40-2__baseline1_best.pt', test=False, use_kl=False, wd=0.0005)

Where could I find those weights or can you release the related teacher weights so that we can download and better configure our experiment environment.

Hi, thanks for your great job! I wrote a kr version using paddle, could you please help see is there any problems? thank you!

https://github.com/littletomatodonkey/code_scipts/blob/main/knowledge_review/knowledge_review.py

I used conv_1x1 for all the channel transform and adaptative avg pool for the size transform.

Thank you very much for your work!

I have noticed that before distillation, the teacher networks are loaded with a pre-trained model. Is the teacher network fixed during distillation, I didn't find where this part of the code (like detach or i.requires_grad = False)

Hi authors, thanks for the great work. But the repository only includes object detectors on Faster RCNN. I want to know when the knowledge distillation of the object detector based on RetinaNet will be released? Thank you!

Hi, thanks for your great job! Where is the mobilenet baseline from? I train the mobilenet for 100epochs and the top1-acc is 69.4%, which seems higher than that provided in the article(68.8%).

Patching CVE-2007-4559

Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

Thanks for your great work! Have you ever apply it on yolox? When i do like this, the loss of it is unstable.I used the output of neck(3 layers),and adapt the teacher channel with student ones.Looking for your reply.Thanks a lot.

Thank you for the nice work! I wonder if you have tried to use ReviewKD loss and KL-divergence loss together? Will the combination further improve the performance? If yes, would you like to share the results or the hyperparameters?

To me, it's confusing, how to set the "shapes" and "out_shapes" when the student is ResNet18 and the teacher is ResNet34 on CIFAR-100.

Is it shapes = out_shapes = [1, 8, 16, 32, 32]

or, shapes = out_shapes = [1, 4, 8, 16, 32]