未验证 提交 91785a45 编写于 作者: L littletomatodonkey 提交者: GitHub

fix dpn (#430)

* fix dpn

* fix se resnext101 metrics
上级 68be3ab2
...@@ -219,7 +219,7 @@ Accuracy and inference time metrics of SEResNeXt and Res2Net series models are s ...@@ -219,7 +219,7 @@ Accuracy and inference time metrics of SEResNeXt and Res2Net series models are s
| SE_ResNet50_vd | 0.7952 | 0.9475 | 4.28393 | 10.38846 | 8.67 | 28.09 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | | SE_ResNet50_vd | 0.7952 | 0.9475 | 4.28393 | 10.38846 | 8.67 | 28.09 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) |
| SE_ResNeXt50_<br>32x4d | 0.7844 | 0.9396 | 8.74121 | 13.563 | 8.02 | 26.16 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | | SE_ResNeXt50_<br>32x4d | 0.7844 | 0.9396 | 8.74121 | 13.563 | 8.02 | 26.16 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) |
| SE_ResNeXt50_vd_<br>32x4d | 0.8024 | 0.9489 | 9.17134 | 14.76192 | 10.76 | 26.28 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_vd_32x4d_pretrained.tar) | | SE_ResNeXt50_vd_<br>32x4d | 0.8024 | 0.9489 | 9.17134 | 14.76192 | 10.76 | 26.28 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_vd_32x4d_pretrained.tar) |
| SE_ResNeXt101_<br>32x4d | 0.7912 | 0.9420 | 18.82604 | 25.31814 | 15.02 | 46.28 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | | SE_ResNeXt101_<br>32x4d | 0.7939 | 0.9443 | 18.82604 | 25.31814 | 15.02 | 46.28 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) |
| SENet154_vd | 0.8140 | 0.9548 | 53.79794 | 66.31684 | 45.83 | 114.29 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) | | SENet154_vd | 0.8140 | 0.9548 | 53.79794 | 66.31684 | 45.83 | 114.29 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) |
......
...@@ -221,7 +221,7 @@ SEResNeXt与Res2Net系列模型的精度、速度指标如下表所示,更多 ...@@ -221,7 +221,7 @@ SEResNeXt与Res2Net系列模型的精度、速度指标如下表所示,更多
| SE_ResNet50_vd | 0.7952 | 0.9475 | 4.28393 | 10.38846 | 8.67 | 28.09 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | | SE_ResNet50_vd | 0.7952 | 0.9475 | 4.28393 | 10.38846 | 8.67 | 28.09 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) |
| SE_ResNeXt50_<br>32x4d | 0.7844 | 0.9396 | 8.74121 | 13.563 | 8.02 | 26.16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | | SE_ResNeXt50_<br>32x4d | 0.7844 | 0.9396 | 8.74121 | 13.563 | 8.02 | 26.16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) |
| SE_ResNeXt50_vd_<br>32x4d | 0.8024 | 0.9489 | 9.17134 | 14.76192 | 10.76 | 26.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_vd_32x4d_pretrained.tar) | | SE_ResNeXt50_vd_<br>32x4d | 0.8024 | 0.9489 | 9.17134 | 14.76192 | 10.76 | 26.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_vd_32x4d_pretrained.tar) |
| SE_ResNeXt101_<br>32x4d | 0.7912 | 0.9420 | 18.82604 | 25.31814 | 15.02 | 46.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | | SE_ResNeXt101_<br>32x4d | 0.7939 | 0.9443 | 18.82604 | 25.31814 | 15.02 | 46.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) |
| SENet154_vd | 0.8140 | 0.9548 | 53.79794 | 66.31684 | 45.83 | 114.29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) | | SENet154_vd | 0.8140 | 0.9548 | 53.79794 | 66.31684 | 45.83 | 114.29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) |
......
...@@ -53,7 +53,7 @@ At present, there are a total of 24 pretrained models of the three categories op ...@@ -53,7 +53,7 @@ At present, there are a total of 24 pretrained models of the three categories op
| SE_ResNet50_vd | 0.795 | 0.948 | | | 8.670 | 28.090 | | SE_ResNet50_vd | 0.795 | 0.948 | | | 8.670 | 28.090 |
| SE_ResNeXt50_32x4d | 0.784 | 0.940 | 0.789 | 0.945 | 8.020 | 26.160 | | SE_ResNeXt50_32x4d | 0.784 | 0.940 | 0.789 | 0.945 | 8.020 | 26.160 |
| SE_ResNeXt50_vd_32x4d | 0.802 | 0.949 | | | 10.760 | 26.280 | | SE_ResNeXt50_vd_32x4d | 0.802 | 0.949 | | | 10.760 | 26.280 |
| SE_ResNeXt101_32x4d | 0.791 | 0.942 | 0.793 | 0.950 | 15.020 | 46.280 | | SE_ResNeXt101_32x4d | 0.7939 | 0.9443 | 0.793 | 0.950 | 15.020 | 46.280 |
| SENet154_vd | 0.814 | 0.955 | | | 45.830 | 114.290 | | SENet154_vd | 0.814 | 0.955 | | | 45.830 | 114.290 |
......
...@@ -52,7 +52,7 @@ Res2Net是2019年提出的一种全新的对ResNet的改进方案,该方案可 ...@@ -52,7 +52,7 @@ Res2Net是2019年提出的一种全新的对ResNet的改进方案,该方案可
| SE_ResNet50_vd | 0.795 | 0.948 | | | 8.670 | 28.090 | | SE_ResNet50_vd | 0.795 | 0.948 | | | 8.670 | 28.090 |
| SE_ResNeXt50_32x4d | 0.784 | 0.940 | 0.789 | 0.945 | 8.020 | 26.160 | | SE_ResNeXt50_32x4d | 0.784 | 0.940 | 0.789 | 0.945 | 8.020 | 26.160 |
| SE_ResNeXt50_vd_32x4d | 0.802 | 0.949 | | | 10.760 | 26.280 | | SE_ResNeXt50_vd_32x4d | 0.802 | 0.949 | | | 10.760 | 26.280 |
| SE_ResNeXt101_32x4d | 0.791 | 0.942 | 0.793 | 0.950 | 15.020 | 46.280 | | SE_ResNeXt101_32x4d | 0.7939 | 0.9443 | 0.793 | 0.950 | 15.020 | 46.280 |
| SENet154_vd | 0.814 | 0.955 | | | 45.830 | 114.290 | | SENet154_vd | 0.814 | 0.955 | | | 45.830 | 114.290 |
......
...@@ -232,7 +232,7 @@ class DPN(nn.Layer): ...@@ -232,7 +232,7 @@ class DPN(nn.Layer):
num_filters=init_num_filter, num_filters=init_num_filter,
filter_size=init_filter_size, filter_size=init_filter_size,
stride=2, stride=2,
pad=1, pad=init_padding,
act='relu', act='relu',
name="conv1") name="conv1")
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册