Skip to content

Commit 0e6223a

Browse files
authored
width_per_group -> width
1 parent 07f917b commit 0e6223a

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

docs/api/paddle/vision/models/ResNet_cn.rst

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -3,18 +3,18 @@
33
ResNet
44
-------------------------------
55

6-
.. py:class:: paddle.vision.models.ResNet(Block, depth=50, width=64, num_classes=1000, with_pool=True)
6+
.. py:class:: paddle.vision.models.ResNet(Block, depth=50, width=64, num_classes=1000, with_pool=True, groups=1)
77
88
ResNet模型,来自论文 `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ 。
99

1010
参数
1111
:::::::::
1212
- **Block** (BasicBlock|BottleneckBlock) - 模型的残差模块。
1313
- **depth** (int,可选) - resnet模型的深度。默认值:50。
14-
- **groups** (int,可选) - 各个卷积块的分组数。默认值:1。
15-
- **width_per_group** (int,可选) - 各个卷积块的每个卷积组基础宽度。默认值:64。
14+
- **width** (int,可选) - 各个卷积块的每个卷积组基础宽度。默认值:64。
1615
- **num_classes** (int, 可选) - 最后一个全连接层输出的维度。如果该值小于0,则不定义最后一个全连接层。默认值:1000。
1716
- **with_pool** (bool,可选) - 是否定义最后一个全连接层之前的池化层。默认值:True。
17+
- **groups** (int,可选) - 各个卷积块的分组数。默认值:1。
1818

1919
返回
2020
:::::::::
@@ -35,10 +35,10 @@ ResNet模型,Layer的实例。
3535
resnet50 = ResNet(BottleneckBlock, 50)
3636
3737
# build Wide ResNet model
38-
wide_resnet50_2 = ResNet(BottleneckBlock, 50, width_per_group=64*2)
38+
wide_resnet50_2 = ResNet(BottleneckBlock, 50, width=64*2)
3939
4040
# build ResNeXt model
41-
resnext50_32x4d = ResNet(BottleneckBlock, 50, groups=32, width_per_group=4)
41+
resnext50_32x4d = ResNet(BottleneckBlock, 50, width=4, groups=32)
4242
4343
x = paddle.rand([1, 3, 224, 224])
4444
out = resnet18(x)

0 commit comments

Comments
 (0)