search

Tencent / PocketFlow

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
https://pocketflow.github.io
Other
2.79k stars 490 forks source link

Please provide the performance of the original model as comparison. #280

Closed lee-bin closed 5 years ago

lee-bin commented 5 years ago

Please make sure that this is a documentation issue.

System information

Describe the documentation issue

The document only lists performance after pruned, would you please provide the performance of the original model so that users can get the performance degradation directly?

We welcome contributions by users. Will you be able to update submit a PR to fix the doc Issue?

jiaxiang-wu commented 5 years ago

The classification accuracy of original models are listed in the "Pre-trained Models" page: https://pocketflow.github.io/pre_trained_models/

lee-bin commented 5 years ago

Thanks, I think it's better to list baseline performance besides.

jiaxiang-wu commented 5 years ago

Documentation revised in PR #287.