NPU (HUAWEI Ascend)¶
Please refer to link installing mmcv on NPU Devices.
Here we use 8 NPUs on your computer to train the model with the following command:
bash tools/dist_train.sh configs/ssd/ssd300_coco.py 8
Also, you can use only one NPU to train the model with the following command:
python tools/train.py configs/ssd/ssd300_coco.py
|Model||box AP||mask AP||Config||Download|
If not specially marked, the results are same between results on the NPU and results on the GPU with FP32.
(*) The results on the NPU of these models are aligned with the results of the mixed-precision training on the GPU, but are lower than the results of the FP32. This situation is mainly related to the phase of the model itself in mixed-precision training, users please adjust the hyperparameters to achieve the best result by self.
All above models are provided by Huawei Ascend group.