Merge pull request #273 from littletomatodonkey/static/fix_doc

polish mainpage readme

docs/en/application/transfer_learning_en.md

@@ -57,7 +57,7 @@ It takes 196 times for grid search, and takes 10 times less for Bayesian search.
 
 ## Large-scale image classification
 
-In practical applications, due to the lack of training data, the classification model trained on the ImageNet1k data set is often used as the pretrained model for other image classification tasks. In order to further help solve practical problems, based on ResNet50_vd, Baidu open sourced a self-developed large-scale classification pretrained model, in which the training data contains 100,000 categories and 43 million pictures.
+In practical applications, due to the lack of training data, the classification model trained on the ImageNet1k data set is often used as the pretrained model for other image classification tasks. In order to further help solve practical problems, based on ResNet50_vd, Baidu open sourced a self-developed large-scale classification pretrained model, in which the training data contains 100,000 categories and 43 million pictures. The pretrained model can be downloaded as follows：[**download link**](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_10w_pretrained.tar)
 
 We conducted transfer learning experiments on 6 self-collected datasets,
 

docs/en/models/HRNet_en.md

@@ -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) |
 |:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 | 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_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            |
@@ -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) |
 |-------------|-----------|-------------------|--------------------------|
 | HRNet_W18_C | 224       | 256               | 7.368                    |
+| HRNet_W18_C_ssld | 224       | 256               | 7.368                    |
 | HRNet_W30_C | 224       | 256               | 9.402                    |
 | HRNet_W32_C | 224       | 256               | 9.467                    |
 | 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
 | 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_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_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                     |

docs/en/models/Mobile_en.md

@@ -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_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_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_int8 | 0.761   |         |                   |                   |              |                   |
 | 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
 | MobileNetV3_small_x0_75          | 5.284            | 9.600           |
 | MobileNetV3_small_x0_5           | 3.352            | 7.800           |
 | 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_int8 | 14.395           | 10.000          |
 | 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
 | 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_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_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               |

docs/en/models/ResNeSt_RegNet_en.md

@@ -11,3 +11,12 @@ RegNet was proposed in 2020 by Facebook to deepen the concept of design space. B
 | ResNeSt50_fast_1s1x64d        | 0.8035 | 0.9528|  0.8035 |            -| 8.68     | 26.3   |
 | ResNeSt50        | 0.8102 | 0.9542|  0.8113 |            -| 10.78     | 27.5   |
 | RegNetX_4GF        | 0.7850 | 0.9416|  0.7860 |            -| 8.0     | 22.1   |
+
+
+## Inference speed based on T4 GPU
+
+| 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) |
+|--------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
+| ResNeSt50_fast_1s1x64d          | 224       | 256   | -           | -            | -          | -      |   -    |    -     |
+| ResNeSt50         | 224       | 256               | -           | -            | -          | -      |   -    |    -     |
+| RegNetX_4GF | 224       | 256       | 6.69042    | 8.01664            | 11.60608       | 6.46478     |   11.19862    |    16.89089    |

docs/en/update_history_en.md

 # Release Notes
 
+* 2020.09.07
+    * Add `HRNet_W18_C_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 81.16%.
+    * Add `MobileNetV3_small_x0_35_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 55.55%.
+
 * 2020.07.14
     * Add `Res2Net200_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 85.13%.
     * Add `Fix_ResNet50_vd_ssld_v2` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 84.00%.

docs/zh_CN/application/transfer_learning.md

@@ -57,7 +57,7 @@ Mixup: [False, True]
 
 ## 二、 大规模分类模型
 
-在实际应用中，由于训练数据的匮乏，往往将ImageNet1k数据集训练的分类模型作为预训练模型，进行图像分类的迁移学习。为了进一步助力解决实际问题，基于ResNet50_vd, 百度开源了自研的大规模分类预训练模型，其中训练数据为10万个类别，4300万张图片。
+在实际应用中，由于训练数据的匮乏，往往将ImageNet1k数据集训练的分类模型作为预训练模型，进行图像分类的迁移学习。为了进一步助力解决实际问题，基于ResNet50_vd, 百度开源了自研的大规模分类预训练模型，其中训练数据为10万个类别，4300万张图片。10万类预训练模型的下载地址：[**下载地址**](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_10w_pretrained.tar)
 
 我们在6个自有采集的数据集上进行迁移学习实验，采用一组固定参数以及网格搜索方式，其中训练轮数设置为20epochs，选用ResNet50_vd模型，ImageNet预训练精度为79.12%。实验数据集参数以及模型精度的对比结果如下：
 

docs/zh_CN/models/HRNet.md

@@ -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) |
 |:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 | 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_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            |
@@ -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) |
 |-------------|-----------|-------------------|--------------------------|
 | HRNet_W18_C | 224       | 256               | 7.368                    |
+| HRNet_W18_C_ssld | 224       | 256               | 7.368                    |
 | HRNet_W30_C | 224       | 256               | 9.402                    |
 | HRNet_W32_C | 224       | 256               | 9.467                    |
 | 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，
 | 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_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_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                     |

docs/zh_CN/models/Mobile.md

@@ -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_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_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_int8 | 0.761   |         |                   |                   |              |                   |
 | 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
 | MobileNetV3_small_x0_75          | 5.284            | 9.600           |
 | MobileNetV3_small_x0_5           | 3.352            | 7.800           |
 | 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_int8 | 14.395           | 10.000          |
 | 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
 | 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_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_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               |

docs/zh_CN/models/ResNeSt_RegNet.md

-# ResNeSt以及RegNet网络
+# ResNeSt与RegNet系列
 
 ## 概述
 
@@ -14,3 +14,12 @@ RegNet是由facebook于2020年提出，旨在深化设计空间理念的概念
 | ResNeSt50_fast_1s1x64d        | 0.8035 | 0.9528|  0.8035 |            -| 8.68     | 26.3   |
 | ResNeSt50        | 0.8102 | 0.9542|  0.8113 |            -| 10.78     | 27.5   |
 | RegNetX_4GF        | 0.7850 | 0.9416|  0.7860 |            -| 8.0     | 22.1   |
+
+
+## 基于T4 GPU的预测速度
+
+| 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) |
+|--------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
+| ResNeSt50_fast_1s1x64d          | 224       | 256   | -           | -            | -          | -      |   -    |    -     |
+| ResNeSt50         | 224       | 256               | -           | -            | -          | -      |   -    |    -     |
+| RegNetX_4GF | 224       | 256       | 6.69042    | 8.01664            | 11.60608       | 6.46478     |   11.19862    |    16.89089    |

docs/zh_CN/update_history.md

 # 更新日志
 
+* 2020.09.07
+    * 添加HRNet_W18_C_ssld模型，在ImageNet上Top-1 Acc可达0.81162；添加MobileNetV3_small_x0_35_ssld模型，在ImageNet上Top-1 Acc可达0.5555。
+
 * 2020.07.14
     * 添加Res2Net200_vd_26w_4s_ssld模型，在ImageNet上Top-1 Acc可达85.13%。
     * 添加Fix_ResNet50_vd_ssld_v2模型，，在ImageNet上Top-1 Acc可达84.0%。

ppcls/utils/logger.py

@@ -16,9 +16,6 @@ import logging
 import os
 import datetime
 
-from imp import reload
-reload(logging)
-
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s %(levelname)s: %(message)s",
@@ -26,7 +23,7 @@ logging.basicConfig(
 
 
 def time_zone(sec, fmt):
-    real_time = datetime.datetime.now() + datetime.timedelta(hours=8)
+    real_time = datetime.datetime.now()
     return real_time.timetuple()