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
未验证 提交 31e1b510 编写于 作者: D dyning 提交者： GitHub
浏览文件
操作

Merge pull request #5 from WuHaobo/master 

init docs
上级 ba7a53b7 abe7ee22
显示空白变更内容
内联 并排
Showing with 1248 addition and 0 deletion
docs/Makefile 0 → 100644
浏览文件 @ 31e1b510
# Minimal makefile for Sphinx documentation
#
# You can set these variables from the command line, and also
# from the environment for the first two.
SPHINXOPTS ?=
SPHINXBUILD ?= sphinx-build
SOURCEDIR = .
BUILDDIR = build
# Put it first so that "make" without argument is like "make help".
help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
.PHONY: help Makefile
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
docs/conf.py 0 → 100644
浏览文件 @ 31e1b510
# Configuration file for the Sphinx documentation builder.
#
# This file only contains a selection of the most common options. For a full
# list see the documentation:
# https://www.sphinx-doc.org/en/master/usage/configuration.html
# -- Path setup --------------------------------------------------------------
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#
import os
import sys
import recommonmark
sys.path.insert(0, os.path.abspath('.'))
sys.path.insert(0, os.path.abspath('..'))
exclude_patterns = ['tmp', 'build', 'tools', 'README.md']
# -- Project information -----------------------------------------------------
project = 'PaddleClas'
copyright = '2020, paddlepaddle'
author = 'paddlepaddle'
# -- General configuration ---------------------------------------------------
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.napoleon',
'sphinx.ext.coverage',
'sphinx.ext.viewcode',
'sphinx.ext.mathjax',
'sphinx.ext.githubpages',
'sphinx.ext.napoleon',
'recommonmark',
'sphinx_markdown_tables',
]
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# md file can also be parased
source_suffix = ['.rst', '.md']
# The master toctree document.
master_doc = 'index'
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
#
# This is also used if you do content translation via gettext catalogs.
# Usually you set "language" from the command line for these cases.
language = 'zh'
# -- Options for HTML output -------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
import sphinx_rtd_theme
html_theme = "sphinx_rtd_theme"
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static']
html_logo = './images/logo.png'
docs/images/models/mobile_arm_top1.png
查看替换文件 @ ba7a53b7 浏览文件 @ 31e1b510
docs/images/models/mobile_arm_top1.png

611.4 KB | W: | H:

docs/images/models/mobile_arm_top1.png

480.6 KB | W: | H:

docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
  • 2-up
  • Swipe
  • Onion skin
docs/index.rst 0 → 100644
浏览文件 @ 31e1b510
欢迎使用PaddleClas图像分类库！
================================
.. toctree::
:maxdepth: 1
zh_cn/tutorials/index
zh_cn/models/index
zh_cn/advanced_tutorials/index
zh_cn/application/index
zh_cn/extension/index
zh_cn/competition_support.md
zh_cn/model_zoo.md
zh_cn/change_log.md
zh_cn/faq.md
:math:`PaddlePaddle2020`
\ No newline at end of file
docs/zh_cn/Makefile 0 → 100644
浏览文件 @ 31e1b510
# Minimal makefile for Sphinx documentation
#
# You can set these variables from the command line, and also
# from the environment for the first two.
SPHINXOPTS ?=
SPHINXBUILD ?= sphinx-build
SOURCEDIR = .
BUILDDIR = build
# Put it first so that "make" without argument is like "make help".
help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
.PHONY: help Makefile
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
rm -f $(BUILDDIR)/html/index_en.html
docs/zh_cn/models/DPN_DenseNet.md 0 → 100644
浏览文件 @ 31e1b510
# DPN与DenseNet系列
## 概述
![](../../images/models/DPN.png)
所有模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型概述正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| DenseNet121 | 0.757 | 0.926 | 0.750 | | 5.690 | 7.980 |
| DenseNet161 | 0.786 | 0.941 | 0.778 | | 15.490 | 28.680 |
| DenseNet169 | 0.768 | 0.933 | 0.764 | | 6.740 | 14.150 |
| DenseNet201 | 0.776 | 0.937 | 0.775 | | 8.610 | 20.010 |
| DenseNet264 | 0.780 | 0.939 | 0.779 | | 11.540 | 33.370 |
| DPN68 | 0.768 | 0.934 | 0.764 | 0.931 | 4.030 | 10.780 |
| DPN92 | 0.799 | 0.948 | 0.793 | 0.946 | 12.540 | 36.290 |
| DPN98 | 0.806 | 0.951 | 0.799 | 0.949 | 22.220 | 58.460 |
| DPN107 | 0.809 | 0.953 | 0.802 | 0.951 | 35.060 | 82.970 |
| DPN131 | 0.807 | 0.951 | 0.801 | 0.949 | 30.510 | 75.360 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| DenseNet121 | 3.653 | 4.560 | 5.574 | 11.517 |
| DenseNet161 | 7.826 | 8.936 | 10.970 | 22.554 |
| DenseNet169 | 5.625 | 6.698 | 7.876 | 14.983 |
| DenseNet201 | 7.243 | 8.537 | 10.111 | 18.928 |
| DenseNet264 | 10.882 | 12.539 | 14.645 | 26.455 |
| DPN68 | 10.310 | 11.060 | 14.299 | 29.618 |
| DPN92 | 16.335 | 17.373 | 23.197 | 45.210 |
| DPN98 | 18.975 | 23.073 | 28.902 | 66.280 |
| DPN107 | 24.932 | 28.607 | 37.513 | 89.112 |
| DPN131 | 25.425 | 29.874 | 37.355 | 88.583 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| DenseNet121 | 3.732 | 6.614 | 8.517 | 21.755 |
| DenseNet161 | 8.282 | 14.438 | 19.336 | 51.953 |
| DenseNet169 | 5.705 | 10.074 | 12.432 | 28.756 |
| DenseNet201 | 7.315 | 13.830 | 16.941 | 38.654 |
| DenseNet264 | 10.986 | 21.460 | 25.724 | 56.501 |
| DPN68 | 10.357 | 11.025 | 14.903 | 34.380 |
| DPN92 | 16.067 | 21.315 | 26.176 | 62.126 |
| DPN98 | 18.455 | 26.710 | 36.009 | 104.084 |
| DPN107 | 24.164 | 37.691 | 51.307 | 148.041 |
| DPN131 | 24.761 | 35.806 | 48.401 | 133.233 |
docs/zh_cn/models/EfficientNet_and_ResNeXt101_wsl.md 0 → 100644
浏览文件 @ 31e1b510
# EfficientNet与ResNeXt101_wsl系列
## 概述
![](../../images/models/EfficientNet.png)
更多的模型简介正在持续更新中。
在预测时，图像的crop_size和resize_short_size如下表所示。
| Models | crop_size | resize_short_size |
|:--:|:--:|:--:|
| ResNeXt101_32x8d_wsl | 224 | 256 |
| ResNeXt101_32x16d_wsl | 224 | 256 |
| ResNeXt101_32x32d_wsl | 224 | 256 |
| ResNeXt101_32x48d_wsl | 224 | 256 |
| Fix_ResNeXt101_32x48d_wsl | 320 | 320 |
| EfficientNetB0 | 224 | 256 |
| EfficientNetB1 | 240 | 272 |
| EfficientNetB2 | 260 | 292 |
| EfficientNetB3 | 300 | 332 |
| EfficientNetB4 | 380 | 412 |
| EfficientNetB5 | 456 | 488 |
| EfficientNetB6 | 528 | 560 |
| EfficientNetB7 | 600 | 632 |
| EfficientNetB0_small | 224 | 256 |
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| ResNeXt101_<br>32x8d_wsl | 0.826 | 0.967 | 0.822 | 0.964 | 29.140 | 78.440 |
| ResNeXt101_<br>32x16d_wsl | 0.842 | 0.973 | 0.842 | 0.972 | 57.550 | 152.660 |
| ResNeXt101_<br>32x32d_wsl | 0.850 | 0.976 | 0.851 | 0.975 | 115.170 | 303.110 |
| ResNeXt101_<br>32x48d_wsl | 0.854 | 0.977 | 0.854 | 0.976 | 173.580 | 456.200 |
| Fix_ResNeXt101_<br>32x48d_wsl | 0.863 | 0.980 | 0.864 | 0.980 | 354.230 | 456.200 |
| EfficientNetB0 | 0.774 | 0.933 | 0.773 | 0.935 | 0.720 | 5.100 |
| EfficientNetB1 | 0.792 | 0.944 | 0.792 | 0.945 | 1.270 | 7.520 |
| EfficientNetB2 | 0.799 | 0.947 | 0.803 | 0.950 | 1.850 | 8.810 |
| EfficientNetB3 | 0.812 | 0.954 | 0.817 | 0.956 | 3.430 | 11.840 |
| EfficientNetB4 | 0.829 | 0.962 | 0.830 | 0.963 | 8.290 | 18.760 |
| EfficientNetB5 | 0.836 | 0.967 | 0.837 | 0.967 | 19.510 | 29.610 |
| EfficientNetB6 | 0.840 | 0.969 | 0.842 | 0.968 | 36.270 | 42.000 |
| EfficientNetB7 | 0.843 | 0.969 | 0.844 | 0.971 | 72.350 | 64.920 |
| EfficientNetB0_<br>small | 0.758 | 0.926 | | | 0.720 | 4.650 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| ResNeXt101_<br>32x8d_wsl | 16.063 | 16.342 | 24.914 | 45.035 |
| ResNeXt101_<br>32x16d_wsl | 16.471 | 25.235 | 30.762 | 67.869 |
| ResNeXt101_<br>32x32d_wsl | 29.425 | 37.149 | 50.834 | |
| ResNeXt101_<br>32x48d_wsl | 40.311 | 58.414 | | |
| Fix_ResNeXt101_<br>32x48d_wsl | 43.960 | 86.514 | | |
| EfficientNetB0 | 1.759 | 2.748 | 3.761 | 10.178 |
| EfficientNetB1 | 2.592 | 4.122 | 5.829 | 16.262 |
| EfficientNetB2 | 2.866 | 4.715 | 7.064 | 20.954 |
| EfficientNetB3 | 3.869 | 6.815 | 10.672 | 34.097 |
| EfficientNetB4 | 5.626 | 11.937 | 19.753 | 67.436 |
| EfficientNetB5 | 8.907 | 21.685 | 37.248 | 134.185 |
| EfficientNetB6 | 13.591 | 34.093 | 60.976 | |
| EfficientNetB7 | 20.963 | 56.397 | 103.971 | |
| EfficientNetB0_<br>small | 1.039 | 1.665 | 2.493 | 7.748 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| ResNeXt101_<br>32x8d_wsl | 16.325 | 25.633 | 37.196 | 108.535 |
| ResNeXt101_<br>32x16d_wsl | 25.224 | 40.929 | 62.898 | |
| ResNeXt101_<br>32x32d_wsl | 41.047 | 79.575 | | |
| ResNeXt101_<br>32x48d_wsl | 60.610 | | | |
| Fix_ResNeXt101_<br>32x48d_wsl | 80.280 | | | |
| EfficientNetB0 | 1.902 | 3.296 | 4.361 | 11.319 |
| EfficientNetB1 | 2.908 | 5.093 | 6.900 | 18.015 |
| EfficientNetB2 | 3.324 | 5.832 | 8.357 | 23.371 |
| EfficientNetB3 | 4.557 | 8.526 | 12.485 | 38.124 |
| EfficientNetB4 | 6.767 | 14.742 | 23.218 | 77.590 |
| EfficientNetB5 | 11.097 | 26.642 | 43.590 | |
| EfficientNetB6 | 17.582 | 42.408 | 74.336 | |
| EfficientNetB7 | 26.529 | 70.337 | 126.839 | |
| EfficientNetB0_<br>small | 1.171 | 2.026 | 2.906 | 8.506 |
docs/zh_cn/models/HRNet.md 0 → 100644
浏览文件 @ 31e1b510
# HRNet系列
## 概述
![](../../images/models/HRNet.png)
所有模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型概述正在持续更新中。
## 精度、FLOPS和参数量
| 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_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 |
| HRNet_W44_C | 0.790 | 0.945 | 0.789 | 0.944 | 29.790 | 67.060 |
| HRNet_W48_C | 0.790 | 0.944 | 0.793 | 0.945 | 34.580 | 77.470 |
| HRNet_W64_C | 0.793 | 0.946 | 0.795 | 0.946 | 57.830 | 128.060 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| HRNet_W18_C | 6.188 | 7.207 | 9.149 | 18.221 |
| HRNet_W30_C | 7.941 | 8.851 | 10.540 | 21.129 |
| HRNet_W32_C | 7.904 | 8.890 | 10.752 | 21.159 |
| HRNet_W40_C | 9.233 | 11.600 | 13.927 | 29.868 |
| HRNet_W44_C | 9.917 | 12.119 | 15.555 | 31.948 |
| HRNet_W48_C | 10.198 | 12.399 | 15.572 | 32.210 |
| HRNet_W64_C | 12.264 | 14.552 | 18.251 | 41.106 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| HRNet_W18_C | 6.828 | 8.552 | 11.154 | 30.665 |
| HRNet_W30_C | 8.901 | 11.067 | 14.421 | 43.459 |
| HRNet_W32_C | 8.983 | 11.334 | 14.688 | 44.564 |
| HRNet_W40_C | 10.300 | 14.720 | 20.257 | 64.346 |
| HRNet_W44_C | 11.183 | 15.830 | 25.292 | 73.136 |
| HRNet_W48_C | 11.619 | 16.791 | 26.569 | 77.536 |
| HRNet_W64_C | 14.434 | 20.988 | 35.114 | 117.434 |
docs/zh_cn/models/Inception.md 0 → 100644
浏览文件 @ 31e1b510
# Inception系列
## 概述
![](../../images/models/Inception.png)
所有模型在预测时，图像的crop_size设置为299，resize_short_size设置为320。
更多的模型简介正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| GoogLeNet | 0.707 | 0.897 | 0.698 | | 2.880 | 8.460 |
| Xception41 | 0.793 | 0.945 | 0.790 | 0.945 | 16.740 | 22.690 |
| Xception41<br>_deeplab | 0.796 | 0.944 | | | 18.160 | 26.730 |
| Xception65 | 0.810 | 0.955 | | | 25.950 | 35.480 |
| Xception65<br>_deeplab | 0.803 | 0.945 | | | 27.370 | 39.520 |
| Xception71 | 0.811 | 0.955 | | | 31.770 | 37.280 |
| InceptionV4 | 0.808 | 0.953 | 0.800 | 0.950 | 24.570 | 42.680 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| GoogLeNet | 1.428 | 1.833 | 2.138 | 4.143 |
| Xception41 | 1.545 | 2.772 | 4.961 | 18.447 |
| Xception41<br>_deeplab | 1.630 | 2.647 | 4.462 | 16.354 |
| Xception65 | 5.398 | 4.215 | 8.611 | 28.702 |
| Xception65<br>_deeplab | 5.317 | 3.688 | 6.168 | 23.108 |
| Xception71 | 2.732 | 5.033 | 8.948 | 33.857 |
| InceptionV4 | 6.172 | 7.558 | 9.527 | 24.021 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| GoogLeNet | 1.436 | 2.904 | 3.800 | 9.049 |
| Xception41 | 3.402 | 7.889 | 14.953 | 56.142 |
| Xception41<br>_deeplab | 3.778 | 8.396 | 15.449 | 58.735 |
| Xception65 | 6.802 | 13.935 | 34.301 | 87.256 |
| Xception65<br>_deeplab | 8.583 | 12.132 | 22.917 | 87.983 |
| Xception71 | 6.156 | 14.359 | 27.360 | 107.282 |
| InceptionV4 | 10.384 | 17.438 | 23.312 | 68.777 |
docs/zh_cn/models/Mobile.md 0 → 100644
浏览文件 @ 31e1b510
# 移动端系列
## 概述
![](../../images/models/mobile_arm_top1.png)
![](../../images/models/mobile_arm_storage.png)
![](../../images/models/mobile_trt.png)
所有模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型概述正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| MobileNetV1_x0_25 | 0.514 | 0.755 | 0.506 | | 0.070 | 0.460 |
| MobileNetV1_x0_5 | 0.635 | 0.847 | 0.637 | | 0.280 | 1.310 |
| MobileNetV1_x0_75 | 0.688 | 0.882 | 0.684 | | 0.630 | 2.550 |
| MobileNetV1 | 0.710 | 0.897 | 0.706 | | 1.110 | 4.190 |
| MobileNetV1_ssld | 0.779 | 0.939 | | | 1.110 | 4.190 |
| MobileNetV2_x0_25 | 0.532 | 0.765 | | | 0.050 | 1.500 |
| MobileNetV2_x0_5 | 0.650 | 0.857 | 0.654 | 0.864 | 0.170 | 1.930 |
| MobileNetV2_x0_75 | 0.698 | 0.890 | 0.698 | 0.896 | 0.350 | 2.580 |
| MobileNetV2 | 0.722 | 0.907 | 0.718 | 0.910 | 0.600 | 3.440 |
| MobileNetV2_x1_5 | 0.741 | 0.917 | | | 1.320 | 6.760 |
| MobileNetV2_x2_0 | 0.752 | 0.926 | | | 2.320 | 11.130 |
| MobileNetV2_ssld | 0.7674 | 0.9339 | | | 0.600 | 3.440 |
| MobileNetV3_large_<br>x1_25 | 0.764 | 0.930 | 0.766 | | 0.714 | 7.440 |
| MobileNetV3_large_<br>x1_0 | 0.753 | 0.753 | 0.752 | | 0.450 | 5.470 |
| MobileNetV3_large_<br>x0_75 | 0.731 | 0.911 | 0.733 | | 0.296 | 3.910 |
| MobileNetV3_large_<br>x0_5 | 0.692 | 0.885 | 0.688 | | 0.138 | 2.670 |
| MobileNetV3_large_<br>x0_35 | 0.643 | 0.855 | 0.642 | | 0.077 | 2.100 |
| MobileNetV3_small_<br>x1_25 | 0.707 | 0.895 | 0.704 | | 0.195 | 3.620 |
| MobileNetV3_small_<br>x1_0 | 0.682 | 0.881 | 0.675 | | 0.123 | 2.940 |
| 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_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 |
| ShuffleNetV2 | 0.688 | 0.885 | 0.694 | | 0.280 | 2.260 |
| ShuffleNetV2_x0_25 | 0.499 | 0.738 | | | 0.030 | 0.600 |
| ShuffleNetV2_x0_33 | 0.537 | 0.771 | | | 0.040 | 0.640 |
| ShuffleNetV2_x0_5 | 0.603 | 0.823 | 0.603 | | 0.080 | 1.360 |
| ShuffleNetV2_x1_5 | 0.716 | 0.902 | 0.726 | | 0.580 | 3.470 |
| ShuffleNetV2_x2_0 | 0.732 | 0.912 | 0.749 | | 1.120 | 7.320 |
| ShuffleNetV2_swish | 0.700 | 0.892 | | | 0.290 | 2.260 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| MobileNetV1_x0_25 | 0.236 | 0.258 | 0.281 | 0.556 |
| MobileNetV1_x0_5 | 0.246 | 0.318 | 0.364 | 0.845 |
| MobileNetV1_x0_75 | 0.303 | 0.380 | 0.512 | 1.164 |
| MobileNetV1 | 0.340 | 0.426 | 0.601 | 1.578 |
| MobileNetV1_ssld | 0.340 | 0.426 | 0.601 | 1.578 |
| MobileNetV2_x0_25 | 0.432 | 0.488 | 0.532 | 0.967 |
| MobileNetV2_x0_5 | 0.475 | 0.564 | 0.654 | 1.296 |
| MobileNetV2_x0_75 | 0.553 | 0.653 | 0.821 | 1.761 |
| MobileNetV2 | 0.610 | 0.738 | 0.931 | 2.115 |
| MobileNetV2_x1_5 | 0.731 | 0.966 | 1.252 | 3.152 |
| MobileNetV2_x2_0 | 0.870 | 1.123 | 1.494 | 3.910 |
| MobileNetV2_ssld | 0.610 | 0.738 | 0.931 | 2.115 |
| MobileNetV3_large_<br>x1_25 | 2.004 | 2.223 | 2.433 | 5.954 |
| MobileNetV3_large_<br>x1_0 | 1.943 | 2.203 | 2.113 | 4.823 |
| MobileNetV3_large_<br>x0_75 | 2.107 | 2.266 | 2.120 | 3.968 |
| MobileNetV3_large_<br>x0_5 | 1.942 | 2.178 | 2.179 | 2.936 |
| MobileNetV3_large_<br>x0_35 | 1.994 | 2.407 | 2.285 | 2.420 |
| MobileNetV3_small_<br>x1_25 | 1.876 | 2.141 | 2.118 | 3.423 |
| MobileNetV3_small_<br>x1_0 | 1.751 | 2.160 | 2.203 | 2.830 |
| MobileNetV3_small_<br>x0_75 | 1.856 | 2.235 | 2.166 | 2.464 |
| MobileNetV3_small_<br>x0_5 | 1.773 | 2.304 | 2.242 | 2.133 |
| MobileNetV3_small_<br>x0_35 | 1.870 | 2.392 | 2.323 | 2.101 |
| MobileNetV3_large_<br>x1_0_ssld | 1.943 | 2.203 | 2.113 | 4.823 | |
| MobileNetV3_small_<br>x1_0_ssld | 1.751 | 2.160 | 2.203 | 2.830 |
| ShuffleNetV2 | 1.134 | 1.068 | 1.199 | 2.558 |
| ShuffleNetV2_x0_25 | 0.911 | 0.953 | 0.948 | 1.327 |
| ShuffleNetV2_x0_33 | 0.853 | 1.072 | 0.958 | 1.398 |
| ShuffleNetV2_x0_5 | 0.858 | 1.059 | 1.084 | 1.620 |
| ShuffleNetV2_x1_5 | 1.040 | 1.153 | 1.394 | 3.452 |
| ShuffleNetV2_x2_0 | 1.061 | 1.316 | 1.694 | 4.485 |
| ShuffleNetV2_swish | 1.688 | 1.958 | 1.707 | 3.711 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| MobileNetV1_x0_25 | 0.233 | 0.372 | 0.424 | 0.930 |
| MobileNetV1_x0_5 | 0.281 | 0.532 | 0.677 | 1.808 |
| MobileNetV1_x0_75 | 0.344 | 0.733 | 0.960 | 2.920 |
| MobileNetV1 | 0.420 | 0.963 | 1.462 | 4.769 |
| MobileNetV1_ssld | 0.420 | 0.963 | 1.462 | 4.769 |
| MobileNetV2_x0_25 | 0.718 | 0.738 | 0.775 | 1.482 |
| MobileNetV2_x0_5 | 0.818 | 0.975 | 1.107 | 2.481 |
| MobileNetV2_x0_75 | 0.830 | 1.104 | 1.514 | 3.629 |
| MobileNetV2 | 0.889 | 1.346 | 1.875 | 4.711 |
| MobileNetV2_x1_5 | 1.221 | 1.982 | 2.951 | 7.645 |
| MobileNetV2_x2_0 | 1.546 | 2.625 | 3.734 | 10.429 |
| MobileNetV2_ssld | 0.889 | 1.346 | 1.875 | 4.711 |
| MobileNetV3_large_<br>x1_25 | 2.113 | 2.377 | 3.114 | 7.332 |
| MobileNetV3_large_<br>x1_0 | 1.991 | 2.380 | 2.517 | 5.826 |
| MobileNetV3_large_<br>x0_75 | 2.105 | 2.454 | 2.336 | 4.611 |
| MobileNetV3_large_<br>x0_5 | 1.978 | 2.603 | 2.291 | 3.306 |
| MobileNetV3_large_<br>x0_35 | 2.017 | 2.469 | 2.316 | 2.558 |
| MobileNetV3_small_<br>x1_25 | 1.915 | 2.411 | 2.295 | 3.742 |
| MobileNetV3_small_<br>x1_0 | 1.915 | 2.889 | 2.862 | 3.022 |
| MobileNetV3_small_<br>x0_75 | 1.941 | 2.358 | 2.232 | 2.602 |
| MobileNetV3_small_<br>x0_5 | 1.872 | 2.364 | 2.238 | 2.061 |
| MobileNetV3_small_<br>x0_35 | 1.889 | 2.407 | 2.328 | 2.127 |
| MobileNetV3_large_<br>x1_0_ssld | 1.991 | 2.380 | 2.517 | 5.826 |
| MobileNetV3_small_<br>x1_0_ssld | 1.915 | 2.889 | 2.862 | 3.022 |
| ShuffleNetV2 | 1.328 | 1.211 | 1.440 | 3.210 |
| ShuffleNetV2_x0_25 | 0.905 | 0.908 | 0.924 | 1.284 |
| ShuffleNetV2_x0_33 | 0.871 | 1.073 | 0.891 | 1.416 |
| ShuffleNetV2_x0_5 | 0.852 | 1.150 | 1.093 | 1.702 |
| ShuffleNetV2_x1_5 | 0.874 | 1.470 | 1.889 | 4.490 |
| ShuffleNetV2_x2_0 | 1.443 | 1.908 | 2.556 | 6.864 |
| ShuffleNetV2_swish | 1.694 | 1.856 | 2.101 | 3.942 |
## CPU预测速度和存储大小
| Models | batch_size=1(ms) | Storage Size(M) |
|:--:|:--:|:--:|
| MobileNetV1_x0_25 | 3.220 | 1.900 |
| MobileNetV1_x0_5 | 9.580 | 5.200 |
| MobileNetV1_x0_75 | 19.436 | 10.000 |
| MobileNetV1 | 32.523 | 16.000 |
| MobileNetV1_ssld | 32.523 | 16.000 |
| MobileNetV2_x0_25 | 3.799 | 6.100 |
| MobileNetV2_x0_5 | 8.702 | 7.800 |
| MobileNetV2_x0_75 | 15.531 | 10.000 |
| MobileNetV2 | 23.318 | 14.000 |
| MobileNetV2_x1_5 | 45.624 | 26.000 |
| MobileNetV2_x2_0 | 74.292 | 43.000 |
| MobileNetV2_ssld | 23.318 | 14.000 |
| MobileNetV3_large_x1_25 | 28.218 | 29.000 |
| MobileNetV3_large_x1_0 | 19.308 | 21.000 |
| MobileNetV3_large_x0_75 | 13.565 | 16.000 |
| MobileNetV3_large_x0_5 | 7.493 | 11.000 |
| MobileNetV3_large_x0_35 | 5.137 | 8.600 |
| MobileNetV3_small_x1_25 | 9.275 | 14.000 |
| MobileNetV3_small_x1_0 | 6.546 | 12.000 |
| 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_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 |
| ShuffleNetV2 | 10.941 | 9.000 |
| ShuffleNetV2_x0_25 | 2.329 | 2.700 |
| ShuffleNetV2_x0_33 | 2.643 | 2.800 |
| ShuffleNetV2_x0_5 | 4.261 | 5.600 |
| ShuffleNetV2_x1_5 | 19.352 | 14.000 |
| ShuffleNetV2_x2_0 | 34.770 | 28.000 |
| ShuffleNetV2_swish | 16.023 | 9.100 |
docs/zh_cn/models/Others.md 0 → 100644
浏览文件 @ 31e1b510
# 其他模型
## 概述
DarkNet53在预测时，图像的crop_size设置为256，resize_short_size设置为256；其余模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型简介正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| AlexNet | 0.567 | 0.792 | 0.5720 | | 1.370 | 61.090 |
| SqueezeNet1_0 | 0.596 | 0.817 | 0.575 | | 1.550 | 1.240 |
| SqueezeNet1_1 | 0.601 | 0.819 | | | 0.690 | 1.230 |
| VGG11 | 0.693 | 0.891 | | | 15.090 | 132.850 |
| VGG13 | 0.700 | 0.894 | | | 22.480 | 133.030 |
| VGG16 | 0.720 | 0.907 | 0.715 | 0.901 | 30.810 | 138.340 |
| VGG19 | 0.726 | 0.909 | | | 39.130 | 143.650 |
| DarkNet53 | 0.780 | 0.941 | 0.772 | 0.938 | 18.580 | 41.600 |
| ResNet50_ACNet | 0.767 | 0.932 | | | 10.730 | 33.110 |
| ResNet50_ACNet<br>_deploy | 0.767 | 0.932 | | | 8.190 | 25.550 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| AlexNet | 0.684 | 0.740 | 0.810 | 1.481 |
| SqueezeNet1_0 | 0.545 | 0.841 | 1.146 | 3.501 |
| SqueezeNet1_1 | 0.473 | 0.575 | 0.805 | 1.862 |
| VGG11 | 1.096 | 1.655 | 2.396 | 6.728 |
| VGG13 | 1.216 | 2.059 | 3.056 | 9.468 |
| VGG16 | 1.518 | 2.594 | 4.019 | 12.145 |
| VGG19 | 1.817 | 3.124 | 4.886 | 14.958 |
| DarkNet53 | 2.150 | 2.627 | 3.422 | 10.092 | |
| ResNet50_ACNet<br>_deploy | 2.748 | 3.178 | 3.823 | 8.369 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| AlexNet | 0.682 | 0.875 | 1.196 | 3.196 |
| SqueezeNet1_0 | 0.530 | 1.072 | 1.652 | 5.338 |
| SqueezeNet1_1 | 0.439 | 0.787 | 1.164 | 2.973 |
| VGG11 | 1.575 | 3.638 | 6.427 | 23.227 |
| VGG13 | 1.859 | 4.832 | 8.832 | 32.946 |
| VGG16 | 2.316 | 6.420 | 11.936 | 44.719 |
| VGG19 | 2.775 | 8.013 | 14.925 | 57.272 |
| DarkNet53 | 2.648 | 5.727 | 9.616 | 33.664 | |
| ResNet50_ACNet<br>_deploy | 4.544 | 6.873 | 9.627 | 28.283 |
docs/zh_cn/models/ResNet_and_vd.md 0 → 100644
浏览文件 @ 31e1b510
# ResNet及其Vd系列
## 概述
![](../../images/models/ResNet.png)
所有模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型概述正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| ResNet18 | 0.710 | 0.899 | 0.696 | 0.891 | 3.660 | 11.690 |
| ResNet18_vd | 0.723 | 0.908 | | | 4.140 | 11.710 |
| ResNet34 | 0.746 | 0.921 | 0.732 | 0.913 | 7.360 | 21.800 |
| ResNet34_vd | 0.760 | 0.930 | | | 7.390 | 21.820 |
| ResNet50 | 0.765 | 0.930 | 0.760 | 0.930 | 8.190 | 25.560 |
| ResNet50_vc | 0.784 | 0.940 | | | 8.670 | 25.580 |
| ResNet50_vd | 0.791 | 0.944 | 0.792 | 0.946 | 8.670 | 25.580 |
| ResNet50_vd_v2 | 0.798 | 0.949 | | | 8.670 | 25.580 |
| ResNet101 | 0.776 | 0.936 | 0.776 | 0.938 | 15.520 | 44.550 |
| ResNet101_vd | 0.802 | 0.950 | | | 16.100 | 44.570 |
| ResNet152 | 0.783 | 0.940 | 0.778 | 0.938 | 23.050 | 60.190 |
| ResNet152_vd | 0.806 | 0.953 | | | 23.530 | 60.210 |
| ResNet200_vd | 0.809 | 0.953 | | | 30.530 | 74.740 |
| ResNet50_vd_ssld | 0.824 | 0.961 | | | 8.670 | 25.580 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| ResNet18 | 0.966 | 1.076 | 1.263 | 2.656 |
| ResNet18_vd | 1.002 | 1.163 | 1.392 | 3.045 |
| ResNet34 | 1.798 | 1.959 | 2.269 | 4.716 |
| ResNet34_vd | 1.839 | 2.011 | 2.482 | 4.767 |
| ResNet50 | 1.892 | 2.146 | 2.692 | 6.411 |
| ResNet50_vc | 1.903 | 2.094 | 2.677 | 6.096 |
| ResNet50_vd | 1.918 | 2.273 | 2.833 | 6.978 |
| ResNet50_vd_v2 | 1.918 | 2.273 | 2.833 | 6.978 |
| ResNet101 | 3.790 | 4.128 | 4.789 | 10.913 |
| ResNet101_vd | 3.853 | 4.229 | 5.001 | 11.437 |
| ResNet152 | 5.523 | 5.871 | 6.710 | 15.258 |
| ResNet152_vd | 5.503 | 6.003 | 7.001 | 15.716 |
| ResNet200_vd | 7.270 | 7.595 | 8.802 | 19.516 |
| ResNet50_vd_ssld | 1.918 | 2.273 | 2.833 | 6.978 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| ResNet18 | 1.127 | 1.428 | 2.352 | 7.780 |
| ResNet18_vd | 1.142 | 1.532 | 2.584 | 8.441 |
| ResNet34 | 1.936 | 2.409 | 4.197 | 14.442 |
| ResNet34_vd | 1.948 | 2.526 | 4.403 | 15.133 |
| ResNet50 | 2.630 | 4.393 | 6.491 | 20.449 |
| ResNet50_vc | 2.728 | 4.413 | 6.618 | 21.183 |
| ResNet50_vd | 2.649 | 4.522 | 6.771 | 21.552 |
| ResNet50_vd_v2 | 2.649 | 4.522 | 6.771 | 21.552 |
| ResNet101 | 4.747 | 8.015 | 11.555 | 36.739 |
| ResNet101_vd | 4.735 | 8.111 | 11.820 | 37.155 |
| ResNet152 | 6.618 | 11.471 | 16.580 | 51.792 |
| ResNet152_vd | 6.626 | 11.613 | 16.843 | 53.645 |
| ResNet200_vd | 8.540 | 14.770 | 21.554 | 69.053 |
| ResNet50_vd_ssld | 2.649 | 4.522 | 6.771 | 21.552 |
docs/zh_cn/models/SEResNext_and_Res2Net.md 0 → 100644
浏览文件 @ 31e1b510
# SEResNeXt与Res2Net系列
## 概述
![](../../images/models/SeResNeXt.png)
所有模型在预测时，图像的crop_size设置为224，resize_short_size设置为256。
更多的模型概述正在持续更新中。
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| Res2Net50_26w_4s | 0.793 | 0.946 | 0.780 | 0.936 | 8.520 | 25.700 |
| Res2Net50_vd_26w_4s | 0.798 | 0.949 | | | 8.370 | 25.060 |
| Res2Net50_14w_8s | 0.795 | 0.947 | 0.781 | 0.939 | 9.010 | 25.720 |
| Res2Net101_vd_26w_4s | 0.806 | 0.952 | | | 16.670 | 45.220 |
| Res2Net200_vd_26w_4s | 0.812 | 0.957 | | | 31.490 | 76.210 |
| ResNeXt50_32x4d | 0.778 | 0.938 | 0.778 | | 8.020 | 23.640 |
| ResNeXt50_vd_32x4d | 0.796 | 0.946 | | | 8.500 | 23.660 |
| ResNeXt50_64x4d | 0.784 | 0.941 | | | 15.060 | 42.360 |
| ResNeXt50_vd_64x4d | 0.801 | 0.949 | | | 15.540 | 42.380 |
| ResNeXt101_32x4d | 0.787 | 0.942 | 0.788 | | 15.010 | 41.540 |
| ResNeXt101_vd_32x4d | 0.803 | 0.951 | | | 15.490 | 41.560 |
| ResNeXt101_64x4d | 0.784 | 0.945 | 0.796 | | 29.050 | 78.120 |
| ResNeXt101_vd_64x4d | 0.808 | 0.952 | | | 29.530 | 78.140 |
| ResNeXt152_32x4d | 0.790 | 0.943 | | | 22.010 | 56.280 |
| ResNeXt152_vd_32x4d | 0.807 | 0.952 | | | 22.490 | 56.300 |
| ResNeXt152_64x4d | 0.795 | 0.947 | | | 43.030 | 107.570 |
| ResNeXt152_vd_64x4d | 0.811 | 0.953 | | | 43.520 | 107.590 |
| SE_ResNet18_vd | 0.733 | 0.914 | | | 4.140 | 11.800 |
| SE_ResNet34_vd | 0.765 | 0.932 | | | 7.840 | 21.980 |
| 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_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 |
| SENet154_vd | 0.814 | 0.955 | | | 45.830 | 114.290 |
## FP16预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| Res2Net50_26w_4s | 2.625 | 3.338 | 4.670 | 11.939 |
| Res2Net50_vd_26w_4s | 2.642 | 3.480 | 4.862 | 13.089 |
| Res2Net50_14w_8s | 3.393 | 4.237 | 5.473 | 13.979 |
| Res2Net101_vd_26w_4s | 5.128 | 6.190 | 7.995 | 20.534 |
| Res2Net200_vd_26w_4s | 9.594 | 11.131 | 14.278 | 36.258 |
| ResNeXt50_32x4d | 6.795 | 7.102 | 8.444 | 18.938 |
| ResNeXt50_vd_32x4d | 7.455 | 7.231 | 8.891 | 19.849 |
| ResNeXt50_64x4d | 20.279 | 12.343 | 13.633 | 32.772 |
| ResNeXt50_vd_64x4d | 16.325 | 21.773 | 25.007 | 55.329 |
| ResNeXt101_32x4d | 14.847 | 15.092 | 15.847 | 42.681 |
| ResNeXt101_vd_32x4d | 15.227 | 15.139 | 16.603 | 39.371 |
| ResNeXt101_64x4d | 28.221 | 29.455 | 29.873 | 59.415 |
| ResNeXt101_vd_64x4d | 31.051 | 28.160 | 28.915 | 60.525 |
| ResNeXt152_32x4d | 22.961 | 23.167 | 24.173 | 51.621 |
| ResNeXt152_vd_32x4d | 23.259 | 23.469 | 23.886 | 52.085 |
| ResNeXt152_64x4d | 41.930 | 42.441 | 45.985 | 79.405 |
| ResNeXt152_vd_64x4d | 42.778 | 43.281 | 45.017 | 79.728 |
| SE_ResNet18_vd | 1.256 | 1.463 | 1.917 | 4.316 |
| SE_ResNet34_vd | 2.314 | 2.691 | 3.432 | 7.411 |
| SE_ResNet50_vd | 2.884 | 4.051 | 5.421 | 15.013 |
| SE_ResNeXt50_32x4d | 7.973 | 10.613 | 12.788 | 29.091 |
| SE_ResNeXt50_vd_32x4d | 8.340 | 12.245 | 15.253 | 30.399 |
| SE_ResNeXt101_32x4d | 17.324 | 21.004 | 28.541 | 52.888 |
| SENet154_vd | 47.234 | 48.018 | 52.967 | 109.787 |
## FP32预测速度
| Models | batch_size=1<br>(ms) | batch_size=4<br>(ms) | batch_size=8<br>(ms) | batch_size=32<br>(ms) |
|:--:|:--:|:--:|:--:|:--:|
| Res2Net50_26w_4s | 3.711 | 5.855 | 8.450 | 26.084 |
| Res2Net50_vd_26w_4s | 3.651 | 5.986 | 8.747 | 26.772 |
| Res2Net50_14w_8s | 4.549 | 6.863 | 9.492 | 27.049 |
| Res2Net101_vd_26w_4s | 6.658 | 10.870 | 15.364 | 47.054 |
| Res2Net200_vd_26w_4s | 12.017 | 19.871 | 28.330 | 88.645 |
| ResNeXt50_32x4d | 6.747 | 8.862 | 11.961 | 32.782 |
| ResNeXt50_vd_32x4d | 6.746 | 9.037 | 12.279 | 33.496 |
| ResNeXt50_64x4d | 11.577 | 14.570 | 20.425 | 57.979 |
| ResNeXt50_vd_64x4d | 19.219 | 21.454 | 30.943 | 90.950 |
| ResNeXt101_32x4d | 14.652 | 18.082 | 24.148 | 70.200 |
| ResNeXt101_vd_32x4d | 14.927 | 18.454 | 23.894 | 67.334 |
| ResNeXt101_64x4d | 28.726 | 30.999 | 43.169 | 116.282 |
| ResNeXt101_vd_64x4d | 28.350 | 31.186 | 41.315 | 113.655 |
| ResNeXt152_32x4d | 23.578 | 27.323 | 35.588 | 99.121 |
| ResNeXt152_vd_32x4d | 23.548 | 26.879 | 35.091 | 104.832 |
| ResNeXt152_64x4d | 43.214 | 43.339 | 60.990 | 159.381 |
| ResNeXt152_vd_64x4d | 43.998 | 44.510 | 61.094 | 160.601 |
| SE_ResNet18_vd | 1.353 | 1.867 | 3.021 | 9.331 |
| SE_ResNet34_vd | 2.421 | 3.201 | 5.294 | 16.849 |
| SE_ResNet50_vd | 3.403 | 6.023 | 8.721 | 26.978 |
| SE_ResNeXt50_32x4d | 8.339 | 12.689 | 15.471 | 41.562 |
| SE_ResNeXt50_vd_32x4d | 7.849 | 13.530 | 16.810 | 44.020 |
| SE_ResNeXt101_32x4d | 16.853 | 24.409 | 32.666 | 81.806 |
| SENet154_vd | 46.002 | 53.666 | 70.589 | 180.334 |
docs/zh_cn/models/Tricks.md 0 → 100644
浏览文件 @ 31e1b510
# 训练技巧
coming soon......
docs/zh_cn/models/index.rst 0 → 100644
浏览文件 @ 31e1b510
模型库
================================
.. toctree::
:maxdepth: 1
models_intro.md
Tricks.md
ResNet_and_vd.md
Mobile.md
SEResNext_and_Res2Net.md
Inception.md
HRNet.md
DPN_DenseNet.md
EfficientNet_and_ResNeXt101_wsl.md
Others.md
docs/zh_cn/models/models_intro.md 0 → 100644
浏览文件 @ 31e1b510
# 模型库概览
## 概述
基于ImageNet1k分类数据集，PaddleClas支持的25种主流分类网络结构和117个图像分类预训练模型如下表所示，训练技巧、每个系列网络结构的简单介绍和性能评估将在相应章节展现。GPU上的预测时间采用V100和TensorRT，CPU的预测时间是基于骁龙855（SD855）。
![](../../images/models/main_fps_top1.png)
![](../../images/models/mobile_arm_top1.png)
- ResNet及其Vd系列
- ResNet系列([论文地址](http://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html))
- [ResNet18](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar)
- [ResNet34](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar)
- [ResNet50](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar)
- [ResNet101](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar)
- [ResNet152](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar)
- ResNet_vc、ResNet_vd系列([论文地址](https://arxiv.org/abs/1812.01187))
- [ResNet50_vc](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vc_pretrained.tar)
- [ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar)
- [ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_vd_pretrained.tar)
- [ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar)
- [ResNet50_vd_v2](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_v2_pretrained.tar)
- [ResNet101_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar)
- [ResNet152_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar)
- [ResNet200_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar)
- [ResNet50_vd_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar)
- 移动端系列
- MobileNetV3系列([论文地址](https://arxiv.org/abs/1905.02244))
- [MobileNetV3_large_x0_35](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_35_pretrained.tar)
- [MobileNetV3_large_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar)
- [MobileNetV3_large_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_75_pretrained.tar)
- [MobileNetV3_large_x1_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar)
- [MobileNetV3_large_x1_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_25_pretrained.tar)
- [MobileNetV3_small_x0_35](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_35_pretrained.tar)
- [MobileNetV3_small_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_5_pretrained.tar)
- [MobileNetV3_small_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_75_pretrained.tar)
- [MobileNetV3_small_x1_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar)
- [MobileNetV3_small_x1_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_25_pretrained.tar)
- [MobileNetV3_large_x1_0_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar)
- [MobileNetV3_large_x1_0_ssld_int8](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_int8_pretrained.tar)
- [MobileNetV3_small_x1_0_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_ssld_pretrained.tar)
- MobileNetV2系列([论文地址](https://arxiv.org/abs/1801.04381))
- [MobileNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar)
- [MobileNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar)
- [MobileNetV2_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar)
- [MobileNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar)
- [MobileNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar)
- [MobileNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar)
- [MobileNetV2_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_ssld_pretrained.tar)
- MobileNetV1系列([论文地址](https://arxiv.org/abs/1704.04861))
- [MobileNetV1_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar)
- [MobileNetV1_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar)
- [MobileNetV1_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar)
- [MobileNetV1](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar)
- [MobileNetV1_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_ssld_pretrained.tar)
- ShuffleNetV2系列([论文地址](https://arxiv.org/abs/1807.11164))
- [ShuffleNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar)
- [ShuffleNetV2_x0_33](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar)
- [ShuffleNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar)
- [ShuffleNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_pretrained.tar)
- [ShuffleNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar)
- [ShuffleNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar)
- [ShuffleNetV2_swish](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar)
- SEResNeXt与Res2Net系列
- ResNeXt系列([论文地址](https://arxiv.org/abs/1611.05431))
- [ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_32x4d_pretrained.tar)
- [ResNeXt50_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar)
- [ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x4d_pretrained.tar)
- [ResNeXt101_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_64x4d_pretrained.tar)
- [ResNeXt152_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_32x4d_pretrained.tar)
- [ResNeXt152_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_64x4d_pretrained.tar)
- ResNeXt_vd系列
- [ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_32x4d_pretrained.tar)
- [ResNeXt50_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_64x4d_pretrained.tar)
- [ResNeXt101_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_32x4d_pretrained.tar)
- [ResNeXt101_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar)
- [ResNeXt152_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_32x4d_pretrained.tar)
- [ResNeXt152_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_64x4d_pretrained.tar)
- SE_ResNet_vd系列([论文地址](https://arxiv.org/abs/1709.01507))
- [SE_ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet18_vd_pretrained.tar)
- [SE_ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet34_vd_pretrained.tar)
- [SE_ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar)
- SE_ResNeXt系列
- [SE_ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar)
- [SE_ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar)
- SE_ResNeXt_vd系列
- [SE_ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_vd_32x4d_pretrained.tar)
- [SENet154_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar)
- Res2Net系列([论文地址](https://arxiv.org/abs/1904.01169))
- [Res2Net50_26w_4s](https://paddle-imagenet-models-name.bj.bcebos.com/Res2Net50_26w_4s_pretrained.tar)
- [Res2Net50_vd_26w_4s](https://paddle-imagenet-models-name.bj.bcebos.com/Res2Net50_vd_26w_4s_pretrained.tar)
- [Res2Net50_14w_8s](https://paddle-imagenet-models-name.bj.bcebos.com/Res2Net50_14w_8s_pretrained.tar)
- [Res2Net101_vd_26w_4s](https://paddle-imagenet-models-name.bj.bcebos.com/Res2Net101_vd_26w_4s_pretrained.tar)
- [Res2Net200_vd_26w_4s](https://paddle-imagenet-models-name.bj.bcebos.com/Res2Net200_vd_26w_4s_pretrained.tar)
- Inception系列
- GoogLeNet系列([论文地址](https://arxiv.org/pdf/1409.4842.pdf))
- [GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar)
- Inception系列([论文地址](https://arxiv.org/abs/1602.07261))
- [InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar)
- Xception系列([论文地址](http://openaccess.thecvf.com/content_cvpr_2017/html/Chollet_Xception_Deep_Learning_CVPR_2017_paper.html))
- [Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar)
- [Xception41_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_deeplab_pretrained.tar)
- [Xception65](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar)
- [Xception65_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar)
- [Xception71](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar)
- HRNet系列
- HRNet系列([论文地址](https://arxiv.org/abs/1908.07919))
- [HRNet_W18_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W18_C_pretrained.tar)
- [HRNet_W30_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W30_C_pretrained.tar)
- [HRNet_W32_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W32_C_pretrained.tar)
- [HRNet_W40_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W40_C_pretrained.tar)
- [HRNet_W44_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W44_C_pretrained.tar)
- [HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W48_C_pretrained.tar)
- [HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar)
- DPN与DenseNet系列
- DPN系列([论文地址](https://arxiv.org/abs/1707.01629))
- [DPN68](https://paddle-imagenet-models-name.bj.bcebos.com/DPN68_pretrained.tar)
- [DPN92](https://paddle-imagenet-models-name.bj.bcebos.com/DPN92_pretrained.tar)
- [DPN98](https://paddle-imagenet-models-name.bj.bcebos.com/DPN98_pretrained.tar)
- [DPN107](https://paddle-imagenet-models-name.bj.bcebos.com/DPN107_pretrained.tar)
- [DPN131](https://paddle-imagenet-models-name.bj.bcebos.com/DPN131_pretrained.tar)
- DenseNet系列([论文地址](https://arxiv.org/abs/1608.06993))
- [DenseNet121](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet121_pretrained.tar)
- [DenseNet161](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet161_pretrained.tar)
- [DenseNet169](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet169_pretrained.tar)
- [DenseNet201](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet201_pretrained.tar)
- [DenseNet264](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet264_pretrained.tar)
- EfficientNet与ResNeXt101_wsl系列
- EfficientNet系列([论文地址](https://arxiv.org/abs/1905.11946))
- [EfficientNetB0_small](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB0_small_pretrained.tar)
- [EfficientNetB0](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB0_pretrained.tar)
- [EfficientNetB1](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB1_pretrained.tar)
- [EfficientNetB2](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB2_pretrained.tar)
- [EfficientNetB3](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB3_pretrained.tar)
- [EfficientNetB4](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB4_pretrained.tar)
- [EfficientNetB5](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB5_pretrained.tar)
- [EfficientNetB6](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB6_pretrained.tar)
- [EfficientNetB7](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB7_pretrained.tar)
- ResNeXt101_wsl系列([论文地址](https://arxiv.org/abs/1805.00932))
- [ResNeXt101_32x8d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar)
- [ResNeXt101_32x16d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar)
- [ResNeXt101_32x32d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar)
- [ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar)
- [Fix_ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar)
- 其他模型
- AlexNet系列([论文地址](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf))
- [AlexNet](https://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar)
- SqueezeNet系列([论文地址](https://arxiv.org/abs/1602.07360))
- [SqueezeNet1_0](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar)
- [SqueezeNet1_1](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar)
- VGG系列([论文地址](https://arxiv.org/abs/1409.1556))
- [VGG11](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar)
- [VGG13](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar)
- [VGG16](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar)
- [VGG19](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar)
- DarkNet系列([论文地址](https://arxiv.org/abs/1506.02640))
- [DarkNet53](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar)
- ACNet系列([论文地址](https://arxiv.org/abs/1908.03930))
- [ResNet50_ACNet_deploy](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_ACNet_deploy_pretrained.tar)
## 参考文献
[1] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[2] He T, Zhang Z, Zhang H, et al. Bag of tricks for image classification with convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 558-567.
[3] Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 1314-1324.
[4] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
[5] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.
[6] Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 116-131.
[7] Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1492-1500.
[8] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.
[9] Gao S, Cheng M M, Zhao K, et al. Res2net: A new multi-scale backbone architecture[J]. IEEE transactions on pattern analysis and machine intelligence, 2019.
[10] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
[11] Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning[C]//Thirty-first AAAI conference on artificial intelligence. 2017.
[12] Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.
[13] Wang J, Sun K, Cheng T, et al. Deep high-resolution representation learning for visual recognition[J]. arXiv preprint arXiv:1908.07919, 2019.
[14] Chen Y, Li J, Xiao H, et al. Dual path networks[C]//Advances in neural information processing systems. 2017: 4467-4475.
[15] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708.
[16] Tan M, Le Q V. Efficientnet: Rethinking model scaling for convolutional neural networks[J]. arXiv preprint arXiv:1905.11946, 2019.
[17] Mahajan D, Girshick R, Ramanathan V, et al. Exploring the limits of weakly supervised pretraining[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 181-196.
[18] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.
[19] Iandola F N, Han S, Moskewicz M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[J]. arXiv preprint arXiv:1602.07360, 2016.
[20] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[21] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.
[22] Ding X, Guo Y, Ding G, et al. Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 1911-1920.
docs/zh_cn/tutorials/config.md 0 → 100644
浏览文件 @ 31e1b510
# 配置说明
---
## 简介
本文档介绍了PaddleClas配置文件(configs/*.yaml)中各参数的含义，以便您更快的自定义或修改超参数配置。
## 配置详解
### 基础配置
| 参数名字 | 具体含义 | 默认值 | 可选值 |
|:---:|:---:|:---:|:---:|
| mode | 运行模式 | "train" | ["train"," valid"] |
| architecture | 模型结构名字 | "ResNet50_vd" | PaddleClas提供的模型结构 |
| pretrained_model | 预训练模型路径 | "" | Str |
| model_save_dir | 保存模型路径 | "" | Str |
| classes_num | 分类数 | 1000 | int |
| total_images | 总图片数 | 1281167 | int |
| save_interval | 每隔多少个epoch保存模型 | 1 | int |
| validate | 是否在训练时进行评估 | TRUE | bool |
| valid_interval | 每隔多少个epoch进行模型评估 | 1 | int |
| epochs | 训练总epoch数 | | int |
| topk | 评估指标K值大小 | 5 | int |
| image_shape | 图片大小 | [3，224，224] | list, shape: (3,) |
| use_mix | 是否启用mixup | False | ['True', 'False'] |
| ls_epsilon | label_smoothing epsilon值| 0 | float |
### 学习率与优化器
学习率
| 参数名字 | 具体含义 | 默认值 | 可选值 |
|:---:|:---:|:---:|:---:|
| function | decay方法名 | "Linear" | ["Linear", "Cosine", <br> "Piecewise", "CosineWarmup"] |
| params.lr | 初始学习率 | 0.1 | float |
| params.decay_epochs | piecewisedecay中<br>衰减学习率的milestone | | list |
| params.gamma | piecewisedecay中gamma值 | 0.1 | float |
| params.warmup_epoch | warmup轮数 | 5 | int |
| parmas.steps | lineardecay衰减steps数 | 100 | int |
| params.end_lr | lineardecayend_lr值 | 0 | float |
优化器
| 参数名字 | 具体含义 | 默认值 | 可选值 |
|:---:|:---:|:---:|:---:|
| function | 优化器方法名 | "Momentum" | ["Momentum", "RmsProp"] |
| params.momentum | momentum值 | 0.9 | float |
| regularizer.function | 正则化方法名 | "L2" | ["L1", "L2"] |
| regularizer.factor | 正则化系数 | 0.0001 | float |
### 数据读取器与数据处理
| 参数名字 | 具体含义 |
|:---:|:---:|
| batch_size | 批大小 |
| num_workers | 数据读取器worker数量 |
| file_list | train文件列表 |
| data_dir | train文件路径 |
| shuffle_seed | 用来进行shuffle的seed值 |
数据处理
| 功能名字 | 参数名字 | 具体含义 |
|:---:|:---:|:---:|
| DecodeImage | to_rgb | 数据转RGB |
| | to_np | 数据转numpy |
| | channel_first | 按CHW排列的图片数据 |
| RandCropImage | size | 随机裁剪 |
| RandFlipImage | | 随机翻转 |
| NormalizeImage | scale | 归一化scale值 |
| | mean | 归一化均值 |
| | std | 归一化方差 |
| | order | 归一化顺序 |
| ToCHWImage | | 调整为CHW |
| CropImage | size | 裁剪大小 |
| ResizeImage | resize_short | 按短边调整大小 |
mix处理
| 参数名字| 具体含义|
|:---:|:---:|
| MixupOperator.alpha | mixup处理中的alpha值|
docs/zh_cn/tutorials/getting_started.md 0 → 100644
浏览文件 @ 31e1b510
# 开始使用
---
请事先参考[安装指南](install.md)配置运行环境
## 1 设置环境变量
**设置PYTHONPATH环境变量：**
```bash
export PYTHONPATH=path_to_PaddleClas:$PYTHONPATH
```
## 2 模型训练与评估
PaddleClas 提供模型训练与评估脚本：tools/train.py和tools/eval.py
### 2.1 模型训练
```bash
# PaddleClas通过launch方式启动多卡多进程训练
# 通过设置FLAGS_selected_gpus 指定GPU运行卡号
python -m paddle.distributed.launch \
--selected_gpus="0,1,2,3" \
--log_dir=log_ResNet50 \
train.py \
-c ../configs/ResNet/ResNet50.yaml \
```
- 输出日志示例如下：
```
epoch:0 train step:13 loss:7.9561 top1:0.0156 top5:0.1094 lr:0.100000 elapse:0.193
```
可以通过添加-o参数来更新配置
```bash
python -m paddle.distributed.launch \
--selected_gpus="0,1,2,3" \
--log_dir=log_ResNet50_vd \
train.py \
-c ../configs/ResNet/ResNet50_vd.yaml \
-o use_mix=1 \
```
- 输出日志示例如下：
```
epoch:0 train step:522 loss:1.6330 lr:0.100000 elapse:0.210
```
或是直接修改模型对应的yaml配置文件，具体配置参数参考[配置文档](config.md)。
### 2.2 模型评估
```bash
python eval.py \
-c ../configs/eval.yaml \
-o architecture="ResNet50_vd" \
-o pretrained_model=path_to_pretrained_models
```
您可以更改configs/eval.yaml中的architecture字段和pretrained_model字段来配置评估模型，或是通过-o参数更新配置。
docs/zh_cn/tutorials/index.rst 0 → 100644
浏览文件 @ 31e1b510
初级使用
================================
.. toctree::
:maxdepth: 1
install.md
getting_started.md
config.md
docs/zh_cn/tutorials/install.md 0 → 100644
浏览文件 @ 31e1b510
# 安装说明
---
## 1.简介
本章将介绍如何安装PaddleClas及其依赖项，准备ImageNet1k图像分类数据集和下载预训练模型。
## 2.安装PaddlePaddle
运行PaddleClas需要PaddlePaddle Fluid v1.7或更高版本。请按照[安装文档](http://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
使用以下命令进行验证。
```
# 在您的Python解释器中确认PaddlePaddle安装成功
>>> import paddle.fluid as fluid
>>> fluid.install_check.run_check()
# 确认PaddlePaddle版本
python -c "import paddle; print(paddle.__version__)"
```
注意：
- 从源码编译的PaddlePaddle版本号为0.0.0，请确保使用了Fluid v1.7之后的源码编译。
- PaddleClas基于PaddlePaddle高性能的分布式训练能力，若您从源码编译，请确保打开编译选项，**WITH_DISTRIBUTE=ON**。
**环境需求:**
- Python2（官方已不提供更新维护）或Python3 (windows系统仅支持Python3)
- CUDA >= 8.0
- cuDNN >= 5.0
- nccl >= 2.1.2
## 3.安装PaddleClas
**克隆PaddleClas模型库：**
```
cd path_to_clone_PaddleClas
git clone https://github.com/PaddlePaddle/PaddleClas.git
```
**安装Python依赖库：**
Python依赖库在[requirements.txt](https://github.com/PaddlePaddle/PaddleClas/blob/master/requirements.txt)中给出，可通过如下命令安装：
```
pip install --upgrade -r requirements.txt
```
## 4.下载ImageNet1K图像分类数据集
PaddleClas默认支持ImageNet1000分类任务。
在Linux系统下通过如下方式进行数据准备：
```
cd dataset/ILSVRC2012/
sh download_imagenet2012.sh
```
在```download_imagenet2012.sh```脚本中，通过下面三步来准备数据：
**步骤一：** 首先在```image-net.org```网站上完成注册，用于获得一对```Username```和```AccessKey```。
**步骤二：** 从ImageNet官网下载ImageNet-2012的图像数据。训练以及验证数据集会分别被下载到"train" 和 "val" 目录中。注意，ImageNet数据的大小超过140GB，下载非常耗时；已经自行下载ImageNet的用户可以直接将数据按"train" 和 "val" 目录放到```dataset/ILSVRC2012```。
**步骤三：** 下载训练与验证集合对应的标签文件。
* train_list.txt: ImageNet-2012训练集合的标签文件，每一行采用"空格"分隔图像路径与标注，例如：
```
train/n02483708/n02483708_2436.jpeg 369
```
* val_list.txt: ImageNet-2012验证集合的标签文件，每一行采用"空格"分隔图像路径与标注，例如：
```
val/ILSVRC2012_val_00000001.jpeg 65
```
**Windows系统下请用户自行下载ImageNet数据，[label下载链接](http://paddle-imagenet-models.bj.bcebos.com/ImageNet_label.tgz)**
## 5.下载预训练模型
PaddleClas 提供了丰富的预训练模型，支持的模型列表请参考[模型库](../models/models_intro.md)。
通过tools/download.py可以下载所需要的预训练模型。
```bash
python tools/download.py -a ResNet50_vd -p ./pretrained -d True
```
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