add RegNet (#170)

* add model

* add results

* update init

* update readme

* update change log

* update docs

* update url link

* update

README.md

@@ -65,6 +65,7 @@ pip install flowvision==0.1.0
             <li>Res2Net</li>
             <li>EfficientNet</li>  
             <li>GhostNet</li>
+            <li>RegNet</li> 
             <li>ReXNet</li>
             <li>Vision Transformer</li>
             <li>DeiT</li>

docs/source/changelog.md

@@ -15,6 +15,7 @@
 - Support IResNeSt model for face recognition [#160](https://github.com/Oneflow-Inc/vision/pull/160)
 - Support [VAN](https://arxiv.org/abs/2202.09741) model and pretrained weight [#166](https://github.com/Oneflow-Inc/vision/pull/166)
 - Support [Dynamic convolution](https://arxiv.org/abs/1912.03458) module [#166](https://github.com/Oneflow-Inc/vision/pull/169)
+- Support [RegNet](https://arxiv.org/abs/2003.13678) model and pretrained weight [#166](https://github.com/Oneflow-Inc/vision/pull/170)
 
 **Bug Fixes**
 - Fix benchmark normalize mode error [#146](https://github.com/Oneflow-Inc/vision/pull/146)

docs/source/flowvision.models.rst

@@ -26,6 +26,7 @@ architectures for image classification:
 -  `GhostNet`_
 -  `Res2Net`_
 -  `EfficientNet`_
+-  `RegNet`_
 -  `ReXNet`_
 -  `ViT`_
 -  `DeiT`_
@@ -73,6 +74,7 @@ architectures for image classification:
 .. _gMLP: https://arxiv.org/abs/2105.08050
 .. _ConvMixer: https://openreview.net/pdf?id=TVHS5Y4dNvM
 .. _EfficientNet: https://arxiv.org/abs/1905.11946
+.. _RegNet: https://arxiv.org/abs/2003.13678
 .. _ConvNeXt: https://arxiv.org/abs/2201.03545
 .. _RegionViT: https://arxiv.org/pdf/2106.02689.pdf
 .. _VAN: https://arxiv.org/pdf/2202.09741.pdf
@@ -222,6 +224,26 @@ EfficientNet
         efficientnet_b7
 
 
+RegNet
+------------
+.. automodule:: flowvision.models
+    :members:
+        regnet_y_400mf,
+        regnet_y_800mf,
+        regnet_y_1_6gf,
+        regnet_y_3_2gf,
+        regnet_y_8gf,
+        regnet_y_16gf,
+        regnet_y_32gf,
+        regnet_x_400mf,
+        regnet_x_800mf,
+        regnet_x_1_6gf,
+        regnet_x_3_2gf,
+        regnet_x_8gf,
+        regnet_x_16gf,
+        regnet_x_32gf,
+
+
 ReXNet
 ------
 .. automodule:: flowvision.models

flowvision/models/__init__.py

@@ -22,6 +22,7 @@
 from .ghostnet import *
 from .res2net import *
 from .efficientnet import *
+from .regnet import *
 from .vision_transformer import *
 from .convnext import *
 from .poolformer import *