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
环境: Ubuntu18.04,cuda10.1, Torch==1.8.1+cu101, Torchvision==0.9.1+cu101, onnx==1.11.0,onnx-simplifier==0.3.10,onnxoptimizer==0.2.7,onnxruntime==1.11.1
安装: 使用的MQBench是最新的main分支代码。安装过程是按照文档的说明进行安装。
过程: 我运行imagenet_example中的PTQ Adaround 的例子,使用默认的 r18_2_4.yaml ,运行结果没有问题。
尝试对 resnet50 用adaround 进行 weight 4bit activation 8 bit 的量化,并且以 onnx_qnn 形式 deploy。 yaml文件是参照 r18_2_4.yaml 以及 r18_8_8_trt.yaml 。 没有对ptq.py 进行修改。
结果: 日志报了 KeyError: reshape_1 的错误。报错来自 advanced_ptq.py的ptq_reconstruction。
The text was updated successfully, but these errors were encountered:
非常详细的复现步骤!我们会尽快修复
Sorry, something went wrong.
#125
This issue has not received any updates in 120 days. Please reply to this issue if this still unresolved!
Successfully merging a pull request may close this issue.
环境:
Ubuntu18.04,cuda10.1,
Torch==1.8.1+cu101, Torchvision==0.9.1+cu101,
onnx==1.11.0,onnx-simplifier==0.3.10,onnxoptimizer==0.2.7,onnxruntime==1.11.1
安装:
使用的MQBench是最新的main分支代码。安装过程是按照文档的说明进行安装。
过程:
我运行imagenet_example中的PTQ Adaround 的例子,使用默认的 r18_2_4.yaml ,运行结果没有问题。
尝试对 resnet50 用adaround 进行 weight 4bit activation 8 bit 的量化,并且以 onnx_qnn 形式 deploy。
yaml文件是参照 r18_2_4.yaml 以及 r18_8_8_trt.yaml 。
没有对ptq.py 进行修改。
结果:
日志报了 KeyError: reshape_1 的错误。报错来自 advanced_ptq.py的ptq_reconstruction。
The text was updated successfully, but these errors were encountered: