Skip to content

P
PaddleClas

PaddlePaddle / PaddleClas
大约 1 年 前同步成功

通知 115
Star 4999
Fork 1114
P
PaddleClas
提交 7370866c 编写于 作者: littletomatodonkey's avatar littletomatodonkey
浏览文件
操作

fix doc

上级 772a2ebd
显示空白变更内容
内联 并排
Showing with 12 addition and 0 deletion
docs/en/models/HRNet_en.md
浏览文件 @ 7370866c
...@@ -22,6 +22,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC ...@@ -22,6 +22,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) | | Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:| |:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| HRNet_W18_C | 0.769 | 0.934 | 0.768 | 0.934 | 4.140 | 21.290 | | HRNet_W18_C | 0.769 | 0.934 | 0.768 | 0.934 | 4.140 | 21.290 |
| HRNet_W18_C_ssld | 0.816 | 0.958 | 0.768 | 0.934 | 4.140 | 21.290 |
| HRNet_W30_C | 0.780 | 0.940 | 0.782 | 0.942 | 16.230 | 37.710 | | HRNet_W30_C | 0.780 | 0.940 | 0.782 | 0.942 | 16.230 | 37.710 |
| HRNet_W32_C | 0.783 | 0.942 | 0.785 | 0.942 | 17.860 | 41.230 | | HRNet_W32_C | 0.783 | 0.942 | 0.785 | 0.942 | 17.860 | 41.230 |
| HRNet_W40_C | 0.788 | 0.945 | 0.789 | 0.945 | 25.410 | 57.550 | | HRNet_W40_C | 0.788 | 0.945 | 0.789 | 0.945 | 25.410 | 57.550 |
...@@ -35,6 +36,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC ...@@ -35,6 +36,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC
| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) | | Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
|-------------|-----------|-------------------|--------------------------| |-------------|-----------|-------------------|--------------------------|
| HRNet_W18_C | 224 | 256 | 7.368 | | HRNet_W18_C | 224 | 256 | 7.368 |
| HRNet_W18_C_ssld | 224 | 256 | 7.368 |
| HRNet_W30_C | 224 | 256 | 9.402 | | HRNet_W30_C | 224 | 256 | 9.402 |
| HRNet_W32_C | 224 | 256 | 9.467 | | HRNet_W32_C | 224 | 256 | 9.467 |
| HRNet_W40_C | 224 | 256 | 10.739 | | HRNet_W40_C | 224 | 256 | 10.739 |
...@@ -50,6 +52,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC ...@@ -50,6 +52,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) | | Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------| |-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| HRNet_W18_C | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 | | HRNet_W18_C | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 |
| HRNet_W18_C_ssld | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 |
| HRNet_W30_C | 224 | 256 | 8.98077 | 14.08082 | 21.23527 | 9.57594 | 17.35485 | 32.6933 | | HRNet_W30_C | 224 | 256 | 8.98077 | 14.08082 | 21.23527 | 9.57594 | 17.35485 | 32.6933 |
| HRNet_W32_C | 224 | 256 | 8.82415 | 14.21462 | 21.19804 | 9.49807 | 17.72921 | 32.96305 | | HRNet_W32_C | 224 | 256 | 8.82415 | 14.21462 | 21.19804 | 9.49807 | 17.72921 | 32.96305 |
| HRNet_W40_C | 224 | 256 | 11.4229 | 19.1595 | 30.47984 | 12.12202 | 25.68184 | 48.90623 | | HRNet_W40_C | 224 | 256 | 11.4229 | 19.1595 | 30.47984 | 12.12202 | 25.68184 | 48.90623 |
......
docs/en/models/Mobile_en.md
浏览文件 @ 7370866c
...@@ -48,6 +48,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad ...@@ -48,6 +48,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad
| MobileNetV3_small_<br>x0_75 | 0.660 | 0.863 | 0.654 | | 0.088 | 2.370 | | MobileNetV3_small_<br>x0_75 | 0.660 | 0.863 | 0.654 | | 0.088 | 2.370 |
| MobileNetV3_small_<br>x0_5 | 0.592 | 0.815 | 0.580 | | 0.043 | 1.900 | | MobileNetV3_small_<br>x0_5 | 0.592 | 0.815 | 0.580 | | 0.043 | 1.900 |
| MobileNetV3_small_<br>x0_35 | 0.530 | 0.764 | 0.498 | | 0.026 | 1.660 | | MobileNetV3_small_<br>x0_35 | 0.530 | 0.764 | 0.498 | | 0.026 | 1.660 |
| MobileNetV3_small_<br>x0_35_ssld | 0.556 | 0.777 | 0.498 | | 0.026 | 1.660 |
| MobileNetV3_large_<br>x1_0_ssld | 0.790 | 0.945 | | | 0.450 | 5.470 | | MobileNetV3_large_<br>x1_0_ssld | 0.790 | 0.945 | | | 0.450 | 5.470 |
| MobileNetV3_large_<br>x1_0_ssld_int8 | 0.761 | | | | | | | MobileNetV3_large_<br>x1_0_ssld_int8 | 0.761 | | | | | |
| MobileNetV3_small_<br>x1_0_ssld | 0.713 | 0.901 | | | 0.123 | 2.940 | | MobileNetV3_small_<br>x1_0_ssld | 0.713 | 0.901 | | | 0.123 | 2.940 |
...@@ -89,6 +90,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad ...@@ -89,6 +90,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad
| MobileNetV3_small_x0_75 | 5.284 | 9.600 | | MobileNetV3_small_x0_75 | 5.284 | 9.600 |
| MobileNetV3_small_x0_5 | 3.352 | 7.800 | | MobileNetV3_small_x0_5 | 3.352 | 7.800 |
| MobileNetV3_small_x0_35 | 2.635 | 6.900 | | MobileNetV3_small_x0_35 | 2.635 | 6.900 |
| MobileNetV3_small_x0_35_ssld | 2.635 | 6.900 |
| MobileNetV3_large_x1_0_ssld | 19.308 | 21.000 | | MobileNetV3_large_x1_0_ssld | 19.308 | 21.000 |
| MobileNetV3_large_x1_0_ssld_int8 | 14.395 | 10.000 | | MobileNetV3_large_x1_0_ssld_int8 | 14.395 | 10.000 |
| MobileNetV3_small_x1_0_ssld | 6.546 | 12.000 | | MobileNetV3_small_x1_0_ssld | 6.546 | 12.000 |
...@@ -130,6 +132,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad ...@@ -130,6 +132,7 @@ Currently there are 32 pretrained models of the mobile series open source by Pad
| MobileNetV3_small_x0_75 | 1.80617 | 2.64646 | 3.24513 | 1.93697 | 2.64285 | 3.32797 | | MobileNetV3_small_x0_75 | 1.80617 | 2.64646 | 3.24513 | 1.93697 | 2.64285 | 3.32797 |
| MobileNetV3_small_x0_5 | 1.95001 | 2.74014 | 3.39485 | 1.88406 | 2.99601 | 3.3908 | | MobileNetV3_small_x0_5 | 1.95001 | 2.74014 | 3.39485 | 1.88406 | 2.99601 | 3.3908 |
| MobileNetV3_small_x0_35 | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 | | MobileNetV3_small_x0_35 | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 |
| MobileNetV3_small_x0_35_ssld | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 |
| MobileNetV3_large_x1_0_ssld | 2.20149 | 3.08423 | 4.07779 | 2.04296 | 2.9322 | 4.53184 | | MobileNetV3_large_x1_0_ssld | 2.20149 | 3.08423 | 4.07779 | 2.04296 | 2.9322 | 4.53184 |
| MobileNetV3_small_x1_0_ssld | 1.73933 | 2.59478 | 3.40276 | 1.74527 | 2.63565 | 3.28124 | | MobileNetV3_small_x1_0_ssld | 1.73933 | 2.59478 | 3.40276 | 1.74527 | 2.63565 | 3.28124 |
| ShuffleNetV2 | 1.95064 | 2.15928 | 2.97169 | 1.89436 | 2.26339 | 3.17615 | | ShuffleNetV2 | 1.95064 | 2.15928 | 2.97169 | 1.89436 | 2.26339 | 3.17615 |
......
docs/zh_CN/models/HRNet.md
浏览文件 @ 7370866c
...@@ -21,6 +21,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， ...@@ -21,6 +21,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络，
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) | | Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:| |:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| HRNet_W18_C | 0.769 | 0.934 | 0.768 | 0.934 | 4.140 | 21.290 | | HRNet_W18_C | 0.769 | 0.934 | 0.768 | 0.934 | 4.140 | 21.290 |
| HRNet_W18_C_ssld | 0.816 | 0.958 | 0.768 | 0.934 | 4.140 | 21.290 |
| HRNet_W30_C | 0.780 | 0.940 | 0.782 | 0.942 | 16.230 | 37.710 | | HRNet_W30_C | 0.780 | 0.940 | 0.782 | 0.942 | 16.230 | 37.710 |
| HRNet_W32_C | 0.783 | 0.942 | 0.785 | 0.942 | 17.860 | 41.230 | | HRNet_W32_C | 0.783 | 0.942 | 0.785 | 0.942 | 17.860 | 41.230 |
| HRNet_W40_C | 0.788 | 0.945 | 0.789 | 0.945 | 25.410 | 57.550 | | HRNet_W40_C | 0.788 | 0.945 | 0.789 | 0.945 | 25.410 | 57.550 |
...@@ -34,6 +35,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， ...@@ -34,6 +35,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络，
| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) | | Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
|-------------|-----------|-------------------|--------------------------| |-------------|-----------|-------------------|--------------------------|
| HRNet_W18_C | 224 | 256 | 7.368 | | HRNet_W18_C | 224 | 256 | 7.368 |
| HRNet_W18_C_ssld | 224 | 256 | 7.368 |
| HRNet_W30_C | 224 | 256 | 9.402 | | HRNet_W30_C | 224 | 256 | 9.402 |
| HRNet_W32_C | 224 | 256 | 9.467 | | HRNet_W32_C | 224 | 256 | 9.467 |
| HRNet_W40_C | 224 | 256 | 10.739 | | HRNet_W40_C | 224 | 256 | 10.739 |
...@@ -49,6 +51,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， ...@@ -49,6 +51,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络，
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) | | Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------| |-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| HRNet_W18_C | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 | | HRNet_W18_C | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 |
| HRNet_W18_C_ssld | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 |
| HRNet_W30_C | 224 | 256 | 8.98077 | 14.08082 | 21.23527 | 9.57594 | 17.35485 | 32.6933 | | HRNet_W30_C | 224 | 256 | 8.98077 | 14.08082 | 21.23527 | 9.57594 | 17.35485 | 32.6933 |
| HRNet_W32_C | 224 | 256 | 8.82415 | 14.21462 | 21.19804 | 9.49807 | 17.72921 | 32.96305 | | HRNet_W32_C | 224 | 256 | 8.82415 | 14.21462 | 21.19804 | 9.49807 | 17.72921 | 32.96305 |
| HRNet_W40_C | 224 | 256 | 11.4229 | 19.1595 | 30.47984 | 12.12202 | 25.68184 | 48.90623 | | HRNet_W40_C | 224 | 256 | 11.4229 | 19.1595 | 30.47984 | 12.12202 | 25.68184 | 48.90623 |
......
docs/zh_CN/models/Mobile.md
浏览文件 @ 7370866c
...@@ -49,6 +49,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通 ...@@ -49,6 +49,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通
| MobileNetV3_small_<br>x0_75 | 0.660 | 0.863 | 0.654 | | 0.088 | 2.370 | | MobileNetV3_small_<br>x0_75 | 0.660 | 0.863 | 0.654 | | 0.088 | 2.370 |
| MobileNetV3_small_<br>x0_5 | 0.592 | 0.815 | 0.580 | | 0.043 | 1.900 | | MobileNetV3_small_<br>x0_5 | 0.592 | 0.815 | 0.580 | | 0.043 | 1.900 |
| MobileNetV3_small_<br>x0_35 | 0.530 | 0.764 | 0.498 | | 0.026 | 1.660 | | MobileNetV3_small_<br>x0_35 | 0.530 | 0.764 | 0.498 | | 0.026 | 1.660 |
| MobileNetV3_small_<br>x0_35_ssld | 0.556 | 0.777 | 0.498 | | 0.026 | 1.660 |
| MobileNetV3_large_<br>x1_0_ssld | 0.790 | 0.945 | | | 0.450 | 5.470 | | MobileNetV3_large_<br>x1_0_ssld | 0.790 | 0.945 | | | 0.450 | 5.470 |
| MobileNetV3_large_<br>x1_0_ssld_int8 | 0.761 | | | | | | | MobileNetV3_large_<br>x1_0_ssld_int8 | 0.761 | | | | | |
| MobileNetV3_small_<br>x1_0_ssld | 0.713 | 0.901 | | | 0.123 | 2.940 | | MobileNetV3_small_<br>x1_0_ssld | 0.713 | 0.901 | | | 0.123 | 2.940 |
...@@ -90,6 +91,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通 ...@@ -90,6 +91,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通
| MobileNetV3_small_x0_75 | 5.284 | 9.600 | | MobileNetV3_small_x0_75 | 5.284 | 9.600 |
| MobileNetV3_small_x0_5 | 3.352 | 7.800 | | MobileNetV3_small_x0_5 | 3.352 | 7.800 |
| MobileNetV3_small_x0_35 | 2.635 | 6.900 | | MobileNetV3_small_x0_35 | 2.635 | 6.900 |
| MobileNetV3_small_x0_35_ssld | 2.635 | 6.900 |
| MobileNetV3_large_x1_0_ssld | 19.308 | 21.000 | | MobileNetV3_large_x1_0_ssld | 19.308 | 21.000 |
| MobileNetV3_large_x1_0_ssld_int8 | 14.395 | 10.000 | | MobileNetV3_large_x1_0_ssld_int8 | 14.395 | 10.000 |
| MobileNetV3_small_x1_0_ssld | 6.546 | 12.000 | | MobileNetV3_small_x1_0_ssld | 6.546 | 12.000 |
...@@ -131,6 +133,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通 ...@@ -131,6 +133,7 @@ GhostNet是华为于2020年提出的一种全新的轻量化网络结构，通
| MobileNetV3_small_x0_75 | 1.80617 | 2.64646 | 3.24513 | 1.93697 | 2.64285 | 3.32797 | | MobileNetV3_small_x0_75 | 1.80617 | 2.64646 | 3.24513 | 1.93697 | 2.64285 | 3.32797 |
| MobileNetV3_small_x0_5 | 1.95001 | 2.74014 | 3.39485 | 1.88406 | 2.99601 | 3.3908 | | MobileNetV3_small_x0_5 | 1.95001 | 2.74014 | 3.39485 | 1.88406 | 2.99601 | 3.3908 |
| MobileNetV3_small_x0_35 | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 | | MobileNetV3_small_x0_35 | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 |
| MobileNetV3_small_x0_35_ssld | 2.10683 | 2.94267 | 3.44254 | 1.94427 | 2.94116 | 3.41082 |
| MobileNetV3_large_x1_0_ssld | 2.20149 | 3.08423 | 4.07779 | 2.04296 | 2.9322 | 4.53184 | | MobileNetV3_large_x1_0_ssld | 2.20149 | 3.08423 | 4.07779 | 2.04296 | 2.9322 | 4.53184 |
| MobileNetV3_small_x1_0_ssld | 1.73933 | 2.59478 | 3.40276 | 1.74527 | 2.63565 | 3.28124 | | MobileNetV3_small_x1_0_ssld | 1.73933 | 2.59478 | 3.40276 | 1.74527 | 2.63565 | 3.28124 |
| ShuffleNetV2 | 1.95064 | 2.15928 | 2.97169 | 1.89436 | 2.26339 | 3.17615 | | ShuffleNetV2 | 1.95064 | 2.15928 | 2.97169 | 1.89436 | 2.26339 | 3.17615 |
......
Markdown is supported
0% 或 .
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 或