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
使用paddleseg进行模型量化时,发现一个bug,代码链接:
PaddleSeg/slim/quant/qat_train.py
Line 190 in 0a7f654
修改:
quantizer.quantize(model) quant_model = model
env: aistudio 至尊gpu版本
PaddleSeg version: release/2.4 PaddlePaddle version: PaddlePaddle 2.2.2 Operation system: Linux
The text was updated successfully, but these errors were encountered:
Fix by the above PR.
Sorry, something went wrong.
juncaipeng
No branches or pull requests
使用paddleseg进行模型量化时,发现一个bug,代码链接:
PaddleSeg/slim/quant/qat_train.py
Line 190 in 0a7f654
,根据paddleslim(2.0.0)文档,量化模型是inplace的,没有返回值,quant_model = None,所以paddleseg量化时会报错“NoneType object has no attribution 'train'”。
paddleslim(2.0.0)文档:
https://paddleslim.readthedocs.io/zh_CN/develop/api_cn/dygraph/quanter/qat.html
paddleslim(2.0.0)源码:https://github.com/PaddlePaddle/PaddleSlim/blob/c2cbef1afaeca836c7551427ebd31c6889b56f8f/paddleslim/dygraph/quant/quanter.py#L217
修改:
env:
aistudio 至尊gpu版本
PaddleSeg version: release/2.4
PaddlePaddle version: PaddlePaddle 2.2.2
Operation system: Linux
The text was updated successfully, but these errors were encountered: