SpursLipu / YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLO ModelCompression MultidatasetTraining
GNU General Public License v3.0
444 stars 136 forks source link

量化训练报错:TypeError: min(): argument 'input' (position 1) must be Tensor, not NoneType #107

Open tomorrow-rain opened 3 years ago

tomorrow-rain commented 3 years ago

a-bit和w-bit都设置为8,在量化进行到 i == 2,a_bit = 16,w_bit = 16时,出现错误:TypeError: min(): argument 'input' (position 1) must be Tensor, not NoneType,这一次的WarmupForQ中构建模型时的GFLOPS是空,请问是哪里出了问题?

1246886181 commented 3 years ago

请问你其他模型的额cfg能训练吗,我的训练时出现AssertionError,加载预训练模型失败

tomorrow-rain commented 3 years ago

请问你其他模型的额cfg能训练吗,我的训练时出现AssertionError,加载预训练模型失败

能训练,你看看在命令中有加“-pt”吗?如果加载预训练模型,需要这个

1246886181 commented 3 years ago

好的,谢谢

---原始邮件--- 发件人: @.> 发送时间: 2021年3月28日(周日) 上午10:24 收件人: @.>; 抄送: @.**@.>; 主题: Re: [SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone] 量化训练报错:TypeError: min(): argument 'input' (position 1) must be Tensor, not NoneType (#107)

请问你其他模型的额cfg能训练吗,我的训练时出现AssertionError,加载预训练模型失败

能训练,你看看在命令中有加“-pt”吗?如果加载预训练模型,需要这个

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.