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

[feature] update npu results, add dist_train_arm.sh #1218

Merged
merged 3 commits into from
Nov 28, 2022
Merged

[feature] update npu results, add dist_train_arm.sh #1218

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
12b39d7
update npu results
wangjiangben-hw Nov 23, 2022
cce2726
add dist_train_arm.sh & updata docs
wangjiangben-hw Nov 24, 2022
a6a0720
del content
wangjiangben-hw Nov 24, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
update npu results
  • Loading branch information
@wangjiangben-hw
wangjiangben-hw committed Nov 23, 2022
commit 12b39d74f937f7fd30b6bfb15d0da1c2715eaaf7
42 changes: 27 additions & 15 deletions docs/en/device/npu.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,28 +7,40 @@ Please install MMCV with NPU device support according to {external+mmcv:doc}`the
Here we use 8 NPUs on your computer to train the model with the following command:

```shell
bash tools/dist_train.sh configs/cspnet/resnet50_8xb32_in1k.py 8 --device npu
bash tools/dist_train.sh configs/resnet/resnet50_8xb32_in1k.py 8 --device npu
```

Also, you can use only one NPU to trian the model with the following command:
Also, you can use only one NPU to train the model with the following command:

```shell
python tools/train.py configs/cspnet/resnet50_8xb32_in1k.py --device npu
python tools/train.py configs/resnet/resnet50_8xb32_in1k.py --device npu
```

## Verified Models

| Model | Top-1 (%) | Top-5 (%) | Config | Download |
| :--------------------------------------------------------: | :-------: | :-------: | :-----------------------------------------------------------: | :-------------------------------------------------------------: |
| [CSPResNeXt50](../papers/cspnet.md) | 77.10 | 93.55 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/cspnet/cspresnext50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/cspresnext50_8xb32_in1k.log.json) |
| [DenseNet121](../papers/densenet.md) | 72.62 | 91.04 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/densenet/densenet121_4xb256_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/densenet121_4xb256_in1k.log.json) |
| [EfficientNet-B4(AA + AdvProp)](../papers/efficientnet.md) | 75.55 | 92.86 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/efficientnet/efficientnet-b4_8xb32-01norm_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/efficientnet-b4_8xb32-01norm_in1k.log.json) |
| [HRNet-W18](../papers/hrnet.md) | 77.01 | 93.46 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hrnet/hrnet-w18_4xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/hrnet-w18_4xb32_in1k.log.json) |
| [ResNetV1D-152](../papers/resnet.md) | 77.11 | 94.54 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d152_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnetv1d152_8xb32_in1k.log.json) |
| [ResNet-50](../papers/resnet.md) | 76.38 | 93.22 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnet50_8xb32_in1k.log) |
| [ResNetXt-32x4d-50](../papers/resnext.md) | 77.55 | 93.75 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext50-32x4d_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnext50-32x4d_8xb32_in1k.log.json) |
| [SE-ResNet-50](../papers/seresnet.md) | 77.64 | 93.76 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/seresnet/seresnet50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/seresnet50_8xb32_in1k.log.json) |
| [VGG-11](../papers/vgg.md) | 68.92 | 88.83 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg11_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/vgg11_8xb32_in1k.log.json) |
| [ShuffleNetV2 1.0x](../papers/shufflenet_v2.md) | 69.53 | 88.82 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/shufflenet-v2-1x_16xb64_in1k.json) |
| Model | Top-1 (%) | Top-5 (%) | Config | Download |
| :---------------------------------------------------------: | :-------: | :-------: | :----------------------------------------------------------: | :-------------------------------------------------------------: |
| [ResNet-50](../papers/resnet.md) | 76.38 | 93.22 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnet50_8xb32_in1k.log) |
| [ResNetXt-32x4d-50](../papers/resnext.md) | 77.55 | 93.75 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext50-32x4d_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnext50-32x4d_8xb32_in1k.log.json) |
| [HRNet-W18](../papers/hrnet.md) | 77.01 | 93.46 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hrnet/hrnet-w18_4xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/hrnet-w18_4xb32_in1k.log.json) |
| [ResNetV1D-152](../papers/resnet.md) | 79.11 | 94.54 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d152_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/resnetv1d152_8xb32_in1k.log.json) |
| [SE-ResNet-50](../papers/seresnet.md) | 77.64 | 93.76 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/seresnet/seresnet50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/seresnet50_8xb32_in1k.log.json) |
| [VGG-11](../papers/vgg.md) | 68.92 | 88.83 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vgg/vgg11_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/vgg11_8xb32_in1k.log.json) |
| [ShuffleNetV2 1.0x](../papers/shufflenet_v2.md) | 69.53 | 88.82 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/shufflenet-v2-1x_16xb64_in1k.json) |
| [MobileNetV2](../papers/mobilenet_v2.md) | 71.758 | 90.394 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/mobilenet_v2/mobilenet-v2_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/mobilenet-v2_8xb32_in1k.json) |
| [MobileNetV3-Small](../papers/mobilenet_v3.md) | 67.522 | 87.316 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/mobilenet_v3/mobilenet-v3-small_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/mobilenet-v3-small_8xb32_in1k.json) |
| [\*CSPResNeXt50](../papers/cspnet.md) | 77.10 | 93.55 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/cspnet/cspresnext50_8xb32_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/cspresnext50_8xb32_in1k.log.json) |
| [\*EfficientNet-B4(AA + AdvProp)](../papers/efficientnet.md) | 75.55 | 92.86 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/efficientnet/efficientnet-b4_8xb32-01norm_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/efficientnet-b4_8xb32-01norm_in1k.log.json) |
| [\*\*DenseNet121](../papers/densenet.md) | 72.62 | 91.04 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/densenet/densenet121_4xb256_in1k.py) | [model](<>) \| [log](https://download.openmmlab.com/mmclassification/v0/device/npu/densenet121_4xb256_in1k.log.json) |

**Notes:**

- If not specially marked, the results are almost same between results on the NPU and results on the GPU with FP32.
- (\*) The training results of these models are lower than the results on the readme in the corresponding model, mainly
because the results on the readme are directly the weight of the timm of the eval, and the results on this side are
retrained according to the config with mmcls. The results of the config training on the GPU are consistent with the
results of the NPU.
- (\*\*) The accuracy of this model is slightly lower because config is a 4-card config, we use 8 cards to run, and users
can adjust hyperparameters to get the best accuracy results.

**All above models are provided by Huawei Ascend group.**