blackfeather-wang/gfnet-pytorch

A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

gfnet-pytorch's Issues

How do you plot the MobileNet-V3,EfficientNet,etc inFigure4

Thanks for your great work which inspires me a lot.
I understand the process of budgeted batch classification, you set a threshold to every classifier, so you can calcuate the FLOPs via different stages with a rate. But in the baseline in figure4 just like MobileNet-V3,EfficientNet, how do you get the result of multi flops with different accuracy. You esemble them with early-exit? or other settings? Thank you.

How to set flops in inference.py

I am interested in your project and your paper.
I find flops = checkpoint['flops'] in inference.py. But when I train a new model by myself, I couldn't find 'flops' during the process of saving checkpoint.
I think I can set this parameter manually. But what should I based on, if I want to set this parameter manually?
Looking forward to your reply.

老哥，我在跑你代码的时候，看到了inference.py里有个flops = checkpoint['flops']，但是，我看了训练和保存模型代码，这些部分并没有设定这个flops，我就想在inference过程里手动设定一下，但是我应该按啥标准来设定这个列表呀？期待你的回复。

training code

great job~ waitting for training code

Missing License

Thank you for sharing your code with the community.

Please consider adding an open-source license to the repository.

Thanks.

How to reproduce this code?

Where does your 'dynamic_threshold' come from?

I find you have dynamic_threshold = checkpoint['dynamic_threshold '] in inference.py and this code is necessary when eval_mode=1. But where does 'dynamic_threshold' come from? You did not save this value when you saved you checkpoint.

Could you release the code for visualization

Could you release the code for visualization？I think visualization would be more intuitive for understanding the dynamic process. Thank you!

very nice work!

very great work,great paper ,l have a question just is for example,in first layer Classifier fc,l know fc is RNN,but l dont know what is the fc to next fc pass through h1C,thanks,vevy nice!

请问为什么不训练某些特定prime model

您好，非常感谢您代码的分享，我想训练一个轻量级的模型，比如mobilenetv3_small_100，但并没有提供预训练模型。如果prime model因为with torch.no_grad()而无法更新网络，效果应该会受到影响。期待您的回复！

Test Code

Hello,
Thanks for your great work, it's a really fascinating
Can you release the code for visualization ? I mean how can we see the sequence of patches in network ?