diff --git a/README.md b/README.md index d129e7d04e5..7a711c87412 100644 --- a/README.md +++ b/README.md @@ -33,6 +33,8 @@ [🆕 Update News](https://mmclassification.readthedocs.io/en/latest/changelog.html) | [🤔 Reporting Issues](https://github.com/open-mmlab/mmclassification/issues/new/choose) +:point_right: **MMClassification 1.0 branch is in trial, welcome every to [try it](https://github.com/open-mmlab/mmclassification/tree/1.x) and [discuss with us](https://github.com/open-mmlab/mmclassification/discussions)!** :point_left: + ## Introduction @@ -62,6 +64,11 @@ The MMClassification 1.0 has released! It's still unstable and in release candid to [the 1.x branch](https://github.com/open-mmlab/mmclassification/tree/1.x) and discuss it with us in [the discussion](https://github.com/open-mmlab/mmclassification/discussions). +v0.24.1 was released in 31/10/2022. +Highlights of the new version: + +- Support HUAWEI Ascend device. + v0.24.0 was released in 30/9/2022. Highlights of the new version: diff --git a/README_zh-CN.md b/README_zh-CN.md index 9e407d1c22f..60f06209d78 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -33,6 +33,10 @@ [🆕 更新日志](https://mmclassification.readthedocs.io/en/latest/changelog.html) | [🤔 报告问题](https://github.com/open-mmlab/mmclassification/issues/new/choose) +:point_right: **MMClassification 1.0 版本即将正式发布，欢迎大家 [试用](https://github.com/open-mmlab/mmclassification/tree/1.x) 并 [参与讨论](https://github.com/open-mmlab/mmclassification/discussions)！** :point_left: + + + ## Introduction @@ -59,6 +63,10 @@ MMClassification 是一款基于 PyTorch 的开源图像分类工具箱，是 [O MMClassification 1.0 已经发布！目前仍在公测中，如果希望试用，请切换到 [1.x 分支](https://github.com/open-mmlab/mmclassification/tree/1.x)，并在[讨论版](https://github.com/open-mmlab/mmclassification/discussions) 参加开发讨论！ +2022/10/31 发布了 v0.24.1 版本 + +- 支持了华为昇腾 NPU 设备。 + 2022/9/30 发布了 v0.24.0 版本 - 支持了 **HorNet**，**EfficientFormerm**，**SwinTransformer V2**，**MViT** 等主干网络。 @@ -66,8 +74,6 @@ MMClassification 1.0 已经发布！目前仍在公测中，如果希望试用 2022/5/1 发布了 v0.23.0 版本 -新版本亮点： - - 支持了 **DenseNet**，**VAN** 和 **PoolFormer** 三个网络，并提供了预训练模型。 - 支持在 IPU 上进行训练。 - 更新了 API 文档的样式，更方便查阅，[欢迎查阅](https://mmclassification.readthedocs.io/en/master/api/models.html)。 diff --git a/docker/serve/Dockerfile b/docker/serve/Dockerfile index b7481d2f5e6..3056e9053e9 100644 --- a/docker/serve/Dockerfile +++ b/docker/serve/Dockerfile @@ -3,8 +3,8 @@ ARG CUDA="10.2" ARG CUDNN="7" FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel -ARG MMCV="1.6.2" -ARG MMCLS="0.24.0" +ARG MMCV="1.7.0" +ARG MMCLS="0.24.1" ENV PYTHONUNBUFFERED TRUE diff --git a/docs/en/_static/css/readthedocs.css b/docs/en/_static/css/readthedocs.css index 5263f47e0ba..577a67a88fa 100644 --- a/docs/en/_static/css/readthedocs.css +++ b/docs/en/_static/css/readthedocs.css @@ -9,12 +9,19 @@ pre { white-space: pre; } -article.pytorch-article .section :not(dt) > code { +article.pytorch-article section code { padding: .2em .4em; background-color: #f3f4f7; border-radius: 5px; } -table.colwidths-auto td { +/* Disable the change in tables */ +article.pytorch-article section table code { + padding: unset; + background-color: unset; + border-radius: unset; +} + +table.autosummary td { width: 50% } diff --git a/docs/en/changelog.md b/docs/en/changelog.md index f478cfab74e..c044f4baf5f 100644 --- a/docs/en/changelog.md +++ b/docs/en/changelog.md @@ -1,5 +1,15 @@ # Changelog +## v0.24.1(31/10/2022) + +### New Features + +- Support mmcls with NPU backend. ([#1072](https://github.com/open-mmlab/mmclassification/pull/1072)) + +### Bug Fixes + +- Fix performance issue in convnext DDP train. ([#1098](https://github.com/open-mmlab/mmclassification/pull/1098)) + ## v0.24.0(30/9/2022) ### Highlights diff --git a/docs/en/conf.py b/docs/en/conf.py index 76b99303b96..301696b38f6 100644 --- a/docs/en/conf.py +++ b/docs/en/conf.py @@ -48,7 +48,6 @@ def get_version(): 'sphinx.ext.intersphinx', 'sphinx.ext.napoleon', 'sphinx.ext.viewcode', - 'sphinx_markdown_tables', 'myst_parser', 'sphinx_copybutton', ] diff --git a/docs/en/device/npu.md b/docs/en/device/npu.md new file mode 100644 index 00000000000..281c8f41e00 --- /dev/null +++ b/docs/en/device/npu.md @@ -0,0 +1,34 @@ +# NPU (HUAWEI Ascend) + +## Usage + +Please install MMCV with NPU device support according to {external+mmcv:doc}`the tutorial `. + +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 +``` + +Also, you can use only one NPU to trian the model with the following command: + +```shell +python tools/train.py configs/cspnet/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](<>) | +| [ResNet-50](../papers/resnet.md) | 76.40 | - | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb32_in1k.py) | [model](<>) \| [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) | + +**All above models are provided by Huawei Ascend group.** diff --git a/docs/en/faq.md b/docs/en/faq.md index 6e48a550352..81f32c5f558 100644 --- a/docs/en/faq.md +++ b/docs/en/faq.md @@ -17,8 +17,8 @@ and make sure you fill in all required information in the template. | MMClassification version | MMCV version | | :----------------------: | :--------------------: | - | dev | mmcv>=1.6.0, \<1.7.0 | - | 0.24.0 (master) | mmcv>=1.4.2, \<1.7.0 | + | dev | mmcv>=1.7.0, \<1.9.0 | + | 0.24.1 (master) | mmcv>=1.4.2, \<1.9.0 | | 0.23.2 | mmcv>=1.4.2, \<1.7.0 | | 0.22.1 | mmcv>=1.4.2, \<1.6.0 | | 0.21.0 | mmcv>=1.4.2, \<=1.5.0 | diff --git a/docs/en/index.rst b/docs/en/index.rst index 5fb3a774c5e..d0a15b1d1c5 100644 --- a/docs/en/index.rst +++ b/docs/en/index.rst @@ -78,6 +78,13 @@ You can switch between Chinese and English documentation in the lower-left corne compatibility.md faq.md + +.. toctree:: + :maxdepth: 1 + :caption: Device Support + + device/npu.md + .. toctree:: :caption: Language Switch diff --git a/docs/zh_CN/_static/css/readthedocs.css b/docs/zh_CN/_static/css/readthedocs.css index 5263f47e0ba..577a67a88fa 100644 --- a/docs/zh_CN/_static/css/readthedocs.css +++ b/docs/zh_CN/_static/css/readthedocs.css @@ -9,12 +9,19 @@ pre { white-space: pre; } -article.pytorch-article .section :not(dt) > code { +article.pytorch-article section code { padding: .2em .4em; background-color: #f3f4f7; border-radius: 5px; } -table.colwidths-auto td { +/* Disable the change in tables */ +article.pytorch-article section table code { + padding: unset; + background-color: unset; + border-radius: unset; +} + +table.autosummary td { width: 50% } diff --git a/docs/zh_CN/conf.py b/docs/zh_CN/conf.py index 4a214d874a8..71daf28b028 100644 --- a/docs/zh_CN/conf.py +++ b/docs/zh_CN/conf.py @@ -48,7 +48,6 @@ def get_version(): 'sphinx.ext.intersphinx', 'sphinx.ext.napoleon', 'sphinx.ext.viewcode', - 'sphinx_markdown_tables', 'myst_parser', 'sphinx_copybutton', ] @@ -214,7 +213,7 @@ def get_version(): 'python': ('https://docs.python.org/3', None), 'numpy': ('https://numpy.org/doc/stable', None), 'torch': ('https://pytorch.org/docs/stable/', None), - 'mmcv': ('https://mmcv.readthedocs.io/en/master/', None), + 'mmcv': ('https://mmcv.readthedocs.io/zh_CN/latest/', None), } diff --git a/docs/zh_CN/device/npu.md b/docs/zh_CN/device/npu.md new file mode 100644 index 00000000000..7adcf0e5144 --- /dev/null +++ b/docs/zh_CN/device/npu.md @@ -0,0 +1,34 @@ +# NPU (华为昇腾) + +## 使用方法 + +首先，请参考 {external+mmcv:doc}`教程 ` 安装带有 NPU 支持的 MMCV。 + +使用如下命令，可以利用 8 个 NPU 在机器上训练模型（以 ResNet 为例）： + +```shell +bash tools/dist_train.sh configs/cspnet/resnet50_8xb32_in1k.py 8 --device npu +``` + +或者，使用如下命令，在一个 NPU 上训练模型（以 ResNet 为例）： + +```shell +python tools/train.py configs/cspnet/resnet50_8xb32_in1k.py --device npu +``` + +## 经过验证的模型 + +| 模型 | Top-1 (%) | Top-5 (%) | 配置文件 | 相关下载 | +| :--------------------------------------------------------: | :-------: | :-------: | :------------------------------------------------------------: | :------------------------------------------------------------: | +| [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](<>) | +| [ResNet-50](../papers/resnet.md) | 76.40 | - | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb32_in1k.py) | [model](<>) \| [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](<>) | + +**以上所有模型权重及训练日志均由华为昇腾团队提供** diff --git a/docs/zh_CN/faq.md b/docs/zh_CN/faq.md index 3ea4f38b58b..4f9572226ac 100644 --- a/docs/zh_CN/faq.md +++ b/docs/zh_CN/faq.md @@ -15,8 +15,8 @@ | MMClassification version | MMCV version | | :----------------------: | :--------------------: | - | dev | mmcv>=1.6.0, \<1.7.0 | - | 0.24.0 (master) | mmcv>=1.4.2, \<1.7.0 | + | dev | mmcv>=1.7.0, \<1.9.0 | + | 0.24.1 (master) | mmcv>=1.4.2, \<1.9.0 | | 0.23.2 | mmcv>=1.4.2, \<1.7.0 | | 0.22.1 | mmcv>=1.4.2, \<1.6.0 | | 0.21.0 | mmcv>=1.4.2, \<=1.5.0 | diff --git a/docs/zh_CN/index.rst b/docs/zh_CN/index.rst index 83634b031aa..1de4b829b82 100644 --- a/docs/zh_CN/index.rst +++ b/docs/zh_CN/index.rst @@ -78,6 +78,13 @@ You can switch between Chinese and English documentation in the lower-left corne faq.md +.. toctree:: + :maxdepth: 1 + :caption: 设备支持 + + device/npu.md + + .. toctree:: :caption: 语言切换 diff --git a/mmcls/__init__.py b/mmcls/__init__.py index 96884327965..097c8fef4c5 100644 --- a/mmcls/__init__.py +++ b/mmcls/__init__.py @@ -48,7 +48,7 @@ def digit_version(version_str: str, length: int = 4): mmcv_minimum_version = '1.4.2' -mmcv_maximum_version = '1.7.0' +mmcv_maximum_version = '1.9.0' mmcv_version = digit_version(mmcv.__version__) diff --git a/mmcls/apis/train.py b/mmcls/apis/train.py index 40e9531d400..909b116d163 100644 --- a/mmcls/apis/train.py +++ b/mmcls/apis/train.py @@ -131,7 +131,6 @@ def train_model(model, model = wrap_distributed_model( model, cfg.device, - device_ids=[torch.cuda.current_device()], broadcast_buffers=False, find_unused_parameters=find_unused_parameters) else: @@ -173,6 +172,10 @@ def train_model(model, # fp16 setting fp16_cfg = cfg.get('fp16', None) + + if fp16_cfg is None and device == 'npu': + fp16_cfg = {'loss_scale': 'dynamic'} + if fp16_cfg is not None: if device == 'ipu': from mmcv.device.ipu import IPUFp16OptimizerHook diff --git a/mmcls/datasets/samplers/distributed_sampler.py b/mmcls/datasets/samplers/distributed_sampler.py index a38c5ac1d58..9e78c400693 100644 --- a/mmcls/datasets/samplers/distributed_sampler.py +++ b/mmcls/datasets/samplers/distributed_sampler.py @@ -4,6 +4,7 @@ from mmcls.core.utils import sync_random_seed from mmcls.datasets import SAMPLERS +from mmcls.utils import auto_select_device @SAMPLERS.register_module() @@ -30,7 +31,7 @@ def __init__(self, # in the same order based on the same seed. Then different ranks # could use different indices to select non-overlapped data from the # same data list. - self.seed = sync_random_seed(seed) + self.seed = sync_random_seed(seed, device=auto_select_device()) def __iter__(self): # deterministically shuffle based on epoch diff --git a/mmcls/models/backbones/convnext.py b/mmcls/models/backbones/convnext.py index 1e0a3e9c5ea..00393638aae 100644 --- a/mmcls/models/backbones/convnext.py +++ b/mmcls/models/backbones/convnext.py @@ -36,8 +36,8 @@ def forward(self, x): assert x.dim() == 4, 'LayerNorm2d only supports inputs with shape ' \ f'(N, C, H, W), but got tensor with shape {x.shape}' return F.layer_norm( - x.permute(0, 2, 3, 1), self.normalized_shape, self.weight, - self.bias, self.eps).permute(0, 3, 1, 2) + x.permute(0, 2, 3, 1).contiguous(), self.normalized_shape, + self.weight, self.bias, self.eps).permute(0, 3, 1, 2).contiguous() class ConvNeXtBlock(BaseModule): diff --git a/mmcls/utils/distribution.py b/mmcls/utils/distribution.py index e3da97ee9a6..d57bd2b53ba 100644 --- a/mmcls/utils/distribution.py +++ b/mmcls/utils/distribution.py @@ -16,7 +16,10 @@ def wrap_non_distributed_model(model, device='cuda', dim=0, *args, **kwargs): Returns: model(nn.Module): the model to be parallelized. """ - if device == 'cuda': + if device == 'npu': + from mmcv.device.npu import NPUDataParallel + model = NPUDataParallel(model.npu(), dim=dim, *args, **kwargs) + elif device == 'cuda': from mmcv.parallel import MMDataParallel model = MMDataParallel(model.cuda(), dim=dim, *args, **kwargs) elif device == 'cpu': @@ -49,9 +52,16 @@ def wrap_distributed_model(model, device='cuda', *args, **kwargs): .. [1] https://pytorch.org/docs/stable/generated/torch.nn.parallel. DistributedDataParallel.html """ - if device == 'cuda': + if device == 'npu': + from mmcv.device.npu import NPUDistributedDataParallel + from torch.npu import current_device + model = NPUDistributedDataParallel( + model.npu(), *args, device_ids=[current_device()], **kwargs) + elif device == 'cuda': from mmcv.parallel import MMDistributedDataParallel - model = MMDistributedDataParallel(model.cuda(), *args, **kwargs) + from torch.cuda import current_device + model = MMDistributedDataParallel( + model.cuda(), *args, device_ids=[current_device()], **kwargs) else: raise RuntimeError(f'Unavailable device "{device}"') diff --git a/mmcls/version.py b/mmcls/version.py index 8980d13f498..42df0388647 100644 --- a/mmcls/version.py +++ b/mmcls/version.py @@ -1,6 +1,6 @@ # Copyright (c) OpenMMLab. All rights reserved -__version__ = '0.24.0' +__version__ = '0.24.1' def parse_version_info(version_str): diff --git a/requirements/mminstall.txt b/requirements/mminstall.txt index 48bbea81050..be7abf0204d 100644 --- a/requirements/mminstall.txt +++ b/requirements/mminstall.txt @@ -1 +1 @@ -mmcv-full>=1.4.2,<1.7.0 +mmcv-full>=1.4.2,<1.9.0