We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
作者您好: 您是否方便提供一下论文表1中的ResNet50您训练所得的top-1为77.27的结果权重呢?万分感谢。
The text was updated successfully, but these errors were encountered:
@WYHZQ 抱歉,这个已经没有了。不过训出这个模型的setting很简单,就是标准setting加上label smoothing和cos linearning rate decay。
你也可以很简单的用我们现成的代码训出来,只需要在训练命令上把模型替换掉就行了,把-a fcanet50换成-a resnet50即可。
-a fcanet50
-a resnet50
python -m torch.distributed.launch --nproc_per_node=$NGPUS main.py -a resnet50 --dali_cpu --b 128 --loss-scale 128.0 --opt-level O2 /path/to/your/ImageNet
Sorry, something went wrong.
@WYHZQ 抱歉,这个已经没有了。不过训出这个模型的setting很简单,就是标准setting加上label smoothing和cos linearning rate decay。 你也可以很简单的用我们现成的代码训出来,只需要在训练命令上把模型替换掉就行了,把- 一个fcanet 50换成- 一个resnet 50即可。 - -nproc_per_node=$NGPUS main.py--a resnet 50--dali_cpu --b 128 --损耗等级128.0 --可选级别O2 /路径/到/您的/ImageNet
你也可以很简单的用我们现成的代码训出来,只需要在训练命令上把模型替换掉就行了,把- 一个fcanet 50换成- 一个resnet 50即可。
- 一个fcanet 50
- 一个resnet 50
- -nproc_per_node=$NGPUS main.py--a resnet 50--dali_cpu --b 128 --损耗等级128.0 --可选级别O2 /路径/到/您的/ImageNet
好的,谢谢您的回复!
No branches or pull requests
作者您好:
您是否方便提供一下论文表1中的ResNet50您训练所得的top-1为77.27的结果权重呢?万分感谢。
The text was updated successfully, but these errors were encountered: