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
代码如下:
错误如下: (接上图)
The text was updated successfully, but these errors were encountered:
config没设置具体的量化策略,默认是超参数搜索,导致递归过大,需要指定一下量化策略
Sorry, something went wrong.
建议使用PTQ(离线量化)策略快速尝试量化效果,图中使用的是超参搜索策略,容易因模型结构导致过多的递归次数而报错。 PTQ 设置参考文档:https://github.com/PaddlePaddle/PaddleSlim/blob/develop/example/auto_compression/hyperparameter_tutorial.md#112-%E7%A6%BB%E7%BA%BF%E9%87%8F%E5%8C%96post-traing-quantization
ConfigSpace 版本问题,最新的 ConfigSpace 有bug,会导致上述错误。 建议回退ConfigSpace 版本到0.5.0:
pip uninstall ConigSpace pip install ConfigSpace==0.5.0
https://pypi.org/project/ConfigSpace/0.5.0/ 相关 issue: automl/ConfigSpace#343
如有需要,可以重新打开该 issue,多谢。
ZhangHandi
No branches or pull requests
代码如下:
错误如下:
(接上图)
The text was updated successfully, but these errors were encountered: