add part code

configs/hornet/hornet-base-gf_8xb64_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-base-gf.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=64)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/hornet-base_8xb64_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-base.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=64)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=5.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/hornet-small-gf_8xb64_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-small-gf.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=64)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/hornet-small_8xb64_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-small.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=64)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=5.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/hornet-tiny-gf_8xb128_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-tiny-gf.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=128)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/hornet-tiny_8xb128_in1k.py

+_base_ = [
+    '../_base_/models/hornet/hornet-tiny.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+data = dict(samples_per_gpu=128)
+
+optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=100.0))
+
+custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

configs/hornet/metafile.yml

+Collections:
+  - Name: HorNet
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - AdamW
+        - Weight Decay
+      Architecture:
+        - HorNet
+        - gnConv
+    Paper:
+      URL: https://arxiv.org/abs/2207.14284
+      Title: "HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions"
+    README: configs/hornet/README.md
+    Code:
+      Version: v0.24.0
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.24.0/mmcls/models/backbones/hornet.py
+
+Models:
+  - Name: hornet-tiny_3rdparty_in1k
+    Metadata:
+      FLOPs: 3976156352   # 3.98G
+      Parameters: 22409512      # 22.41M
+    In Collection: HorNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.84
+          Top 5 Accuracy: 96.24
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny_3rdparty_in1k_20220915-0e8eedff.pth
+    Config: configs/hornet/hornet-tiny_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/1ca970586c6043709a3f/?dl=1
+  - Name: hornet-tiny-gf_3rdparty_in1k
+    Metadata:
+      FLOPs: 3896472160   # 3.9G
+      Parameters: 22991848      # 22.99M
+    In Collection: HorNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.98
+          Top 5 Accuracy: 96.38
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny-gf_3rdparty_in1k_20220915-4c35a66b.pth
+    Config: configs/hornet/hornet-tiny-gf_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/511faad0bde94dfcaa54/?dl=1
+  - Name: hornet-small_3rdparty_in1k
+    Metadata:
+      FLOPs:  8825621280    # 8.83G
+      Parameters: 49528264          # 49.53M
+    In Collection: HorNet
+    Results:
+        - Dataset: ImageNet-1k
+          Metrics:
+            Top 1 Accuracy: 83.79
+            Top 5 Accuracy: 96.75
+          Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small_3rdparty_in1k_20220915-5935f60f.pth
+    Config: configs/hornet/hornet-small_8xb64_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/46422799db2941f7b684/?dl=1
+  - Name: hornet-small-gf_3rdparty_in1k
+    Metadata:
+      FLOPs:  8706094992    # 8.71G
+      Parameters: 50401768          # 50.4M
+    In Collection: HorNet
+    Results:
+        - Dataset: ImageNet-1k
+          Metrics:
+            Top 1 Accuracy: 83.98
+            Top 5 Accuracy: 96.77
+          Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small-gf_3rdparty_in1k_20220915-649ca492.pth
+    Config: configs/hornet/hornet-small-gf_8xb64_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/8405c984bf084d2ba85a/?dl=1
+  - Name: hornet-base_3rdparty_in1k
+    Metadata:
+      FLOPs: 15582677376              # 15.59G
+      Parameters: 87256680            # 87.26M
+    In Collection: HorNet
+    Results:
+        - Dataset: ImageNet-1k
+          Metrics:
+            Top 1 Accuracy: 84.24
+            Top 5 Accuracy: 96.94
+          Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base_3rdparty_in1k_20220915-a06176bb.pth
+    Config: configs/hornet/hornet-base_8xb64_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/5c86cb3d655d4c17a959/?dl=1
+  - Name: hornet-base-gf_3rdparty_in1k
+    Metadata:
+      FLOPs: 15423308992              # 15.42G
+      Parameters: 88421352            # 88.42M
+    In Collection: HorNet
+    Results:
+        - Dataset: ImageNet-1k
+          Metrics:
+            Top 1 Accuracy: 84.32
+            Top 5 Accuracy: 96.95
+          Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base-gf_3rdparty_in1k_20220915-82c06fa7.pth
+    Config: configs/hornet/hornet-base-gf_8xb64_in1k.py
+    Converted From:
+      Code: https://github.com/raoyongming/HorNet
+      Weights: https://cloud.tsinghua.edu.cn/f/6c84935e63b547f383fb/?dl=1

configs/hrnet/README.md

+# HRNet
+
+> [Deep High-Resolution Representation Learning for Visual Recognition](https://arxiv.org/abs/1908.07919v2)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions *in series* (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams *in parallel*; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/149920446-cbe05670-989d-4fe6-accc-df20ae2984eb.png" width="100%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('hrnet-w18_3rdparty_8xb32_in1k', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('hrnet-w18_3rdparty_8xb32_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Test:
+
+```shell
+python tools/test.py configs/hrnet/hrnet-w18_4xb32_in1k.py https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32_in1k_20220120-0c10b180.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                  |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |              Config               |                                     Download                                     |
+| :------------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :-------------------------------: | :------------------------------------------------------------------------------: |
+| `hrnet-w18_3rdparty_8xb32_in1k`\*      | From scratch |   21.30    |   4.33    |   76.75   |   93.44   | [config](hrnet-w18_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32_in1k_20220120-0c10b180.pth) |
+| `hrnet-w30_3rdparty_8xb32_in1k`\*      | From scratch |   37.71    |   8.17    |   78.19   |   94.22   | [config](hrnet-w30_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w30_3rdparty_8xb32_in1k_20220120-8aa3832f.pth) |
+| `hrnet-w32_3rdparty_8xb32_in1k`\*      | From scratch |   41.23    |   8.99    |   78.44   |   94.19   | [config](hrnet-w32_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w32_3rdparty_8xb32_in1k_20220120-c394f1ab.pth) |
+| `hrnet-w40_3rdparty_8xb32_in1k`\*      | From scratch |   57.55    |   12.77   |   78.94   |   94.47   | [config](hrnet-w40_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w40_3rdparty_8xb32_in1k_20220120-9a2dbfc5.pth) |
+| `hrnet-w44_3rdparty_8xb32_in1k`\*      | From scratch |   67.06    |   14.96   |   78.88   |   94.37   | [config](hrnet-w44_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w44_3rdparty_8xb32_in1k_20220120-35d07f73.pth) |
+| `hrnet-w48_3rdparty_8xb32_in1k`\*      | From scratch |   77.47    |   17.36   |   79.32   |   94.52   | [config](hrnet-w48_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w48_3rdparty_8xb32_in1k_20220120-e555ef50.pth) |
+| `hrnet-w64_3rdparty_8xb32_in1k`\*      | From scratch |   128.06   |   29.00   |   79.46   |   94.65   | [config](hrnet-w64_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w64_3rdparty_8xb32_in1k_20220120-19126642.pth) |
+| `hrnet-w18_3rdparty_8xb32-ssld_in1k`\* | From scratch |   21.30    |   4.33    |   81.06   |   95.70   | [config](hrnet-w18_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32-ssld_in1k_20220120-455f69ea.pth) |
+| `hrnet-w48_3rdparty_8xb32-ssld_in1k`\* | From scratch |   77.47    |   17.36   |   83.63   |   96.79   | [config](hrnet-w48_4xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w48_3rdparty_8xb32-ssld_in1k_20220120-d0459c38.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/HRNet/HRNet-Image-Classification). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@article{WangSCJDZLMTWLX19,
+  title={Deep High-Resolution Representation Learning for Visual Recognition},
+  author={Jingdong Wang and Ke Sun and Tianheng Cheng and
+          Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and
+          Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao},
+  journal={TPAMI},
+  year={2019}
+}
+```

configs/hrnet/hrnet-w18_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w18.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w30_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w30.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w32_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w32.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w40_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w40.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w44_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w44.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w48_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w48.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/hrnet-w64_4xb32_in1k.py

+_base_ = [
+    '../_base_/models/hrnet/hrnet-w64.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (4 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=128)

configs/hrnet/metafile.yml

+Collections:
+  - Name: HRNet
+    Metadata:
+      Training Data: ImageNet-1k
+      Architecture:
+        - Batch Normalization
+        - Convolution
+        - ReLU
+        - Residual Connection
+    Paper:
+      URL: https://arxiv.org/abs/1908.07919v2
+      Title: "Deep High-Resolution Representation Learning for Visual Recognition"
+    README: configs/hrnet/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.20.1/mmcls/models/backbones/hrnet.py
+      Version: v0.20.1
+
+Models:
+  - Name: hrnet-w18_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 4330397932
+      Parameters: 21295164
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 76.75
+          Top 5 Accuracy: 93.44
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32_in1k_20220120-0c10b180.pth
+    Config: configs/hrnet/hrnet-w18_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33cMkPimlmClRvmpw
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w30_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 8168305684
+      Parameters: 37708380
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.19
+          Top 5 Accuracy: 94.22
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w30_3rdparty_8xb32_in1k_20220120-8aa3832f.pth
+    Config: configs/hrnet/hrnet-w30_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33cQoACCEfrzcSaVI
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w32_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 8986267584
+      Parameters: 41228840
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.44
+          Top 5 Accuracy: 94.19
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w32_3rdparty_8xb32_in1k_20220120-c394f1ab.pth
+    Config: configs/hrnet/hrnet-w32_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w40_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 12767574064
+      Parameters: 57553320
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.94
+          Top 5 Accuracy: 94.47
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w40_3rdparty_8xb32_in1k_20220120-9a2dbfc5.pth
+    Config: configs/hrnet/hrnet-w40_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33ck0gvo5jfoWBOPo
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w44_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 14963902632
+      Parameters: 67061144
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.88
+          Top 5 Accuracy: 94.37
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w44_3rdparty_8xb32_in1k_20220120-35d07f73.pth
+    Config: configs/hrnet/hrnet-w44_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33czZQ0woUb980gRs
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w48_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 17364014752
+      Parameters: 77466024
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.32
+          Top 5 Accuracy: 94.52
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w48_3rdparty_8xb32_in1k_20220120-e555ef50.pth
+    Config: configs/hrnet/hrnet-w48_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33dKvqI6pBZlifgJk
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w64_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 29002298752
+      Parameters: 128056104
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.46
+          Top 5 Accuracy: 94.65
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w64_3rdparty_8xb32_in1k_20220120-19126642.pth
+    Config: configs/hrnet/hrnet-w64_4xb32_in1k.py
+    Converted From:
+      Weights: https://1drv.ms/u/s!Aus8VCZ_C_33gQbJsUPTIj3rQu99
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w18_3rdparty_8xb32-ssld_in1k
+    Metadata:
+      FLOPs: 4330397932
+      Parameters: 21295164
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.06
+          Top 5 Accuracy: 95.7
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32-ssld_in1k_20220120-455f69ea.pth
+    Config: configs/hrnet/hrnet-w18_4xb32_in1k.py
+    Converted From:
+      Weights: https://github.com/HRNet/HRNet-Image-Classification/releases/download/PretrainedWeights/HRNet_W18_C_ssld_pretrained.pth
+      Code: https://github.com/HRNet/HRNet-Image-Classification
+  - Name: hrnet-w48_3rdparty_8xb32-ssld_in1k
+    Metadata:
+      FLOPs: 17364014752
+      Parameters: 77466024
+    In Collection: HRNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.63
+          Top 5 Accuracy: 96.79
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w48_3rdparty_8xb32-ssld_in1k_20220120-d0459c38.pth
+    Config: configs/hrnet/hrnet-w48_4xb32_in1k.py
+    Converted From:
+      Weights: https://github.com/HRNet/HRNet-Image-Classification/releases/download/PretrainedWeights/HRNet_W48_C_ssld_pretrained.pth
+      Code: https://github.com/HRNet/HRNet-Image-Classification

configs/inception_v3/README.md

+# Inception V3
+
+> [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3.5% top-5 error on the validation set (3.6% error on the test set) and 17.3% top-1 error on the validation set.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/177241797-c103eff4-79bb-414d-aef6-eac323b65a50.png" width="40%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('inception-v3_3rdparty_8xb32_in1k', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('inception-v3_3rdparty_8xb32_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Test:
+
+```shell
+python tools/test.py configs/inception_v3/inception-v3_8xb32_in1k.py https://download.openmmlab.com/mmclassification/v0/inception-v3/inception-v3_3rdparty_8xb32_in1k_20220615-dcd4d910.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                Config                |                                    Download                                     |
+| :----------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------: | :-----------------------------------------------------------------------------: |
+| `inception-v3_3rdparty_8xb32_in1k`\* | From scratch |   23.83    |   5.75    |   77.57   |   93.58   | [config](inception-v3_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/inception-v3/inception-v3_3rdparty_8xb32_in1k_20220615-dcd4d910.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py#L28). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@inproceedings{szegedy2016rethinking,
+  title={Rethinking the inception architecture for computer vision},
+  author={Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={2818--2826},
+  year={2016}
+}
+```

configs/inception_v3/inception-v3_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/inception_v3.py',
+    '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py',
+]
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=299),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=342, edge='short'),
+    dict(type='CenterCrop', crop_size=299),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))

configs/inception_v3/metafile.yml

+Collections:
+  - Name: Inception V3
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Epochs: 100
+      Batch Size: 256
+      Architecture:
+        - Inception
+    Paper:
+      URL: http://arxiv.org/abs/1512.00567
+      Title: "Rethinking the Inception Architecture for Computer Vision"
+    README: configs/inception_v3/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v1.0.0rc1/configs/inception_v3/metafile.yml
+      Version: v1.0.0rc1
+
+Models:
+  - Name: inception-v3_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 5745177632
+      Parameters: 23834568
+    In Collection: Inception V3
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.57
+          Top 5 Accuracy: 93.58
+    Weights: https://download.openmmlab.com/mmclassification/v0/inception-v3/inception-v3_3rdparty_8xb32_in1k_20220615-dcd4d910.pth
+    Config: configs/inception_v3/inception-v3_8xb32_in1k.py
+    Converted From:
+      Weights: https://download.pytorch.org/models/inception_v3_google-0cc3c7bd.pth
+      Code: https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py#L28

configs/itpn/README.md

+# iTPN
+
+> [Integrally Pre-Trained Transformer Pyramid Networks](https://arxiv.org/abs/2211.12735)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+In this paper, we present an integral pre-training framework based on masked image modeling (MIM). We advocate for pre-training the backbone and neck jointly so that the transfer gap between MIM and downstream recognition tasks is minimal. We make two technical contributions. First, we unify the reconstruction and recognition necks by inserting a feature pyramid into the pre-training stage. Second, we complement mask image modeling (MIM) with masked feature modeling (MFM) that offers multi-stage supervision to the feature pyramid. The pre-trained models, termed integrally pre-trained transformer pyramid networks (iTPNs), serve as powerful foundation models for visual recognition. In particular, the base/large-level iTPN achieves an 86.2%/87.8% top-1 accuracy on ImageNet-1K, a 53.2%/55.6% box AP on COCO object detection with 1x training schedule using Mask-RCNN, and a 54.7%/57.7% mIoU on ADE20K semantic segmentation using UPerHead -- all these results set new records. Our work inspires the community to work on unifying upstream pre-training and downstream fine-tuning tasks. Code and the pre-trained models will be released at https://github.com/sunsmarterjie/iTPN.
+
+<div align=center>
+<img src="https://github.com/open-mmlab/mmpretrain/assets/36138628/2e53d5b5-300e-4640-8507-c1173965ca62" width="80%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+<!-- **Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+``` -->
+
+**Train/Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Train:
+
+```shell
+python tools/train.py configs/itpn/itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                                   | Params (M) | Flops (G) |                               Config                               | Download |
+| :------------------------------------------------------ | :--------: | :-------: | :----------------------------------------------------------------: | :------: |
+| `itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k` |   233.00   |   18.47   | [config](itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k.py) |   N/A    |
+| `itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k`  |   103.00   |   18.47   | [config](itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py)  |   N/A    |
+| `itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k` |   314.00   |   63.98   | [config](itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k.py) |   N/A    |
+
+## Citation
+
+```bibtex
+@article{tian2022integrally,
+  title={Integrally Pre-Trained Transformer Pyramid Networks},
+  author={Tian, Yunjie and Xie, Lingxi and Wang, Zhaozhi and Wei, Longhui and Zhang, Xiaopeng and Jiao, Jianbin and Wang, Yaowei and Tian, Qi and Ye, Qixiang},
+  journal={arXiv preprint arXiv:2211.12735},
+  year={2022}
+}
+```