Release 2.5.0

What's Changed

XQuant Extension Tool (experimental) (#1502)

• Calculates the error for each layer by comparing the float model and quantized model, using both models along with the quantization log. The results are presented in reports. It identifies the causes of the detected errors and recommends appropriate improvement measures for each cause. Read more Troubleshoot Manual

New CustomLayer: MulticlassNMSOBB (for PyTorch) (#1508)

• Implemented a new CustomLayer: MulticlassNMSOBB, the Non-Maximum Suppression layer for the Object Detection (Oriented Bounding Box) task.

Bug Fixes

• Modify the Stack Layer settings in TPC (v1.0) (#1523)

Tutorials

• Add PyTorch Tutorial of PoseNet: We've added a new PyTorch tutorial of PoseNet model for the Human Pose Estimation task. Try it! (#1524)

Supported Python versions

• Python(>=3.10).(#1551 )