search

Megvii-BaseDetection / YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Apache License 2.0
9.44k stars 2.21k forks source link

Follow the README to run the MegEngine implementation, but report an error #988

Closed milezhao closed 2 years ago

milezhao commented 2 years ago

When I followed the README to run the MegEngine implementation, I got an error like below.

14 07:38:02 WRN try setting the submodule <class 'megengine.tensor.Tensor'> to <class 'models.yolo_head.YOLOXHead'>'s new attribute grids.1, its name grids.0 will remain unchanged 14 07:38:02 WRN try setting the submodule <class 'megengine.tensor.Tensor'> to <class 'models.yolo_head.YOLOXHead'>'s new attribute grids.2, its name grids.0 will remain unchanged

FateScript commented 2 years ago

Don't worry, it's just a warning.