Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom

mnn_offline_quant离线量化失败 #2981

Open
DommyWorld opened this issue Jul 31, 2024 · 1 comment
Open

mnn_offline_quant离线量化失败 #2981

DommyWorld opened this issue Jul 31, 2024 · 1 comment

Comments

@DommyWorld
Copy link

使用mnn_offline_quant离线量化，模型是多输入，量化后算子仍然是float32类型。但量化过程没有报错，模型文件大小有所缩减，但是模型推理速度并没有上升。附上量化前和量化后的模型。
量化后.zip
量化前.zip
@v0jiuqi
Copy link
Collaborator

v0jiuqi commented Aug 26, 2024

多输入的模型可以直接采取权重量化的方式。-MNNConvert --WeightQuantBits这样，具体使用方式参考文档。编译时打开-DMNN_LOW_MEMORY=ON，推理时memory mode使用 low

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@DommyWorld @v0jiuqi