Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.

forresti / SqueezeNet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

BSD 2-Clause "Simplified" License

2.17k stars 723 forks source link

Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1. #47

Open miaow1988 opened 7 years ago

miaow1988 commented 7 years ago

Hi, I've trained a new model based on SqueezeNet V1.1, and it achieved 61% top-1 accuracy on ImageNet without sacrificing parameter numbers and efficiency. I've uploaded my model to this [https://github.com/miaow1988/SqueezeNet_v1.2] repository. Would you please added my repository to your README.md file, so more people could know this work.

Jie

forresti commented 6 years ago

Sorry for the slow reply. I would be interested to learn more about this. I don't have your contact info, so could you send me an email at forrest@deepscale.ai?

ujsyehao commented 6 years ago

Hi, @miaow1988 Can you share your tricks about training squeeze net v1.1 model? Thank you in advance!

ujsyehao commented 6 years ago

@forresti Hi，I follow @miaow1988 tutorial and train the model, It performs better when removing relu after squeeze net layer, Do you have some ideas about it?

syedmustafan commented 3 years ago

@miaow1988 The results by removing RELU were really good.