yehuitang / pruning Goto Github PK

No matter how I train, the recognition rate is always 10%, and the loss is always nan. I tried training from scratch and still got this result.why？

Hi, I'm CNN light-weighting researcher, and I'm building a filter pruning leaderboard for better comparison.
I think GPU hour for search and training is important to evaluate the pruning algorithms, but you didn't report it.
Would you let me know GPU hours for each ImageNet configuration?

Hello. How to get ResNet56 pre-trained model for Cifar10 in the paper SCOP? I was not able to find it in pytorch hub.

Hello,I was running the search.py,and when I run it on Win10,the value pred_fake = netD_B(fake_B.detach()) was positive and it was negative on ubuntu.
Could pred_fake = netD_B(fake_B.detach()) be negative,is it normal?

How could I change hyper-parameter gamma for the compress ratio?

Hi. Thanks for your work. I am currently running your code training with imagenet. It runs, but when the conducting "validate_ontrain

And the loss becomes normal after training the first epoch, but the remain rate you displayed is large even training for hundreds of epochs.

Is it normal? I have loaded the pretrained model

Hi,
Could you please provide more information on how you calculated the FID score? For example, which code did you use? How many images did you use to find FID score?
Thanks in advance.

Hello,
Thank you for your work. It looks amazing and I'd like to try it on some custom dataset.
Could you please share the script with training generator for ImageNet or for another dataset?

After run the command:
python ManiDP/main.py --ngpu=1 --arch=dyresnet56 --dataset=cifar10 --target_remain_rate=0.6 --lambda_lasso 5e-3 --lambda_graph 1.0 --pretrain_path='ManiDP/pretrain_path/' --data_path='...'
the loss is nan.
I think this error is caused by the lasso loss. Can you give some advice. Thanks

Hi,

I'm really interested in your work. I wonder could u please release the pretrained dense model and the pruned model? I'm not sure if your training setting is the same as the default one in the code. Thanks!

I have found that some parts of the mask will extremely increase and become Nan when one sample is input into the MaskBlock, although the clamp_max is set 1000.

Hello, thanks for your work "Manifold Regularized Dynamic Network Pruning",and i'd like to know when will the code be released?

Hello. Thanks for your work. I have some confusions about how the Manidp achieve acceleration.
I found that the convolution is forwarded without masks.

Hello please help me to resolve this issue.

what could be the reason for this error.

Excuse me, could you release the pre-trained-prune models with different super parameter γ（0.1，1，10）, such as netG_A2B_prune_200.pth and netG_B2A_prune_200.pth with γ（0.1，1，10）? I want to learn about it, but my computer need train for a long time .Thank you!

请问一下，在运行过程中发现没有MoXing支持并且缺少部分cache/和相关的.pth文件，并且目前没有使用HUAWEI 云服务器的条件 请问贵团队有没有其他可以运行代码的方法？多谢！O(∩_∩)O

Is the code incomplete?

Hello. I am using the ManiDP code, and I want to train with Cifar10. However, I don't know where to find the pre-train model. Could you provide the pre-train model or the code for original training?

when i run the search.py code appear the problem as in the picture,what should i set in the problem?

How to update the mask of manidp to the network, the output model channel does not change

RT，求问为什么第一次的时候要和后面的迭代过程不一样啊

ModuleNotFoundError: No module named 'moxing'