Repository: incubator-singa
Updated Branches:
  refs/heads/master 59ef841fe -> a515c380d


SINGA-352 Add Chinese documentations for SINGA examples


Project: http://git-wip-us.apache.org/repos/asf/incubator-singa/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-singa/commit/b235e9b6
Tree: http://git-wip-us.apache.org/repos/asf/incubator-singa/tree/b235e9b6
Diff: http://git-wip-us.apache.org/repos/asf/incubator-singa/diff/b235e9b6

Branch: refs/heads/master
Commit: b235e9b6ec313c9bccea5fd33746d5cc89bbcc6f
Parents: c343ff9
Author: Wentong-DST <[email protected]>
Authored: Tue May 22 13:47:45 2018 +0800
Committer: Wentong-DST <[email protected]>
Committed: Tue May 22 13:47:45 2018 +0800

----------------------------------------------------------------------
 doc/en/releases/RELEASE_NOTES_1.2.0.md          |  2 +-
 .../docs/model_zoo/imagenet/densenet/README.md  | 43 +++++++++++++++++
 .../docs/model_zoo/imagenet/inception/README.md | 36 ++++++++++++++
 doc/zh/docs/model_zoo/imagenet/resnet/README.md | 50 ++++++++++++++++++++
 doc/zh/docs/model_zoo/imagenet/vgg/README.md    | 48 +++++++++++++++++++
 doc/zh/docs/model_zoo/index.rst                 |  5 ++
 doc/zh/docs/model_zoo/mnist/README.md           | 18 +++++++
 examples/index.rst                              |  6 ++-
 8 files changed, 206 insertions(+), 2 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/en/releases/RELEASE_NOTES_1.2.0.md
----------------------------------------------------------------------
diff --git a/doc/en/releases/RELEASE_NOTES_1.2.0.md 
b/doc/en/releases/RELEASE_NOTES_1.2.0.md
index 8ebf6d3..ca4ace6 100644
--- a/doc/en/releases/RELEASE_NOTES_1.2.0.md
+++ b/doc/en/releases/RELEASE_NOTES_1.2.0.md
@@ -46,7 +46,7 @@ This release includes following features:
       * [SINGA-361] Add git instructions for contributors and committers
 
   * Bugs fixed
-      * [Singa-330] fix openblas building on i7 7700k
+      * [SINGA-330] fix openblas building on i7 7700k
       * [SINGA-331] Fix the bug of tensor division operation
       * [SINGA-350] Error from python3 test
       * [SINGA-356] Error using travis tool to build SINGA on mac os

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/imagenet/densenet/README.md
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/imagenet/densenet/README.md 
b/doc/zh/docs/model_zoo/imagenet/densenet/README.md
new file mode 100644
index 0000000..ed36fa2
--- /dev/null
+++ b/doc/zh/docs/model_zoo/imagenet/densenet/README.md
@@ -0,0 +1,43 @@
+name: DenseNet on ImageNet SINGA version: 1.1.1 SINGA commit: license: 
https://github.com/pytorch/vision/blob/master/torchvision/models/densenet.py
+
+---
+
+# 用DenseNet做图像分类
+
+
+这个例子中,我们将PyTorch训练好的DenseNet转换为SINGA模型以用作图像分类。
+
+## 操作说明
+
+* 下载参数的checkpoint文件到如下目录
+
+        $ wget 
https://s3-ap-southeast-1.amazonaws.com/dlfile/densenet/densenet-121.tar.gz
+               $ wget 
https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/synset_words.txt
+               $ tar xvf densenet-121.tar.gz
+
+* 运行程序
+
+        $ python serve.py -h
+               
+* 运行程序
+
+        # use cpu
+               $ python serve.py --use_cpu --parameter_file 
densenet-121.pickle --depth 121 &
+               # use gpu
+               $ python serve.py --parameter_file densenet-121.pickle --depth 
121 &
+
+* 提交图片进行分类
+
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+
+image1.jpg, image2.jpg和image3.jpg应该在执行指令前就已被下载。
+
+## 详细信息
+
+用`convert.py`从Pytorch参数文件中提取参数值
+
+* 运行程序
+
+       $ python convert.py -h
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/imagenet/inception/README.md
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/imagenet/inception/README.md 
b/doc/zh/docs/model_zoo/imagenet/inception/README.md
new file mode 100644
index 0000000..3773cd4
--- /dev/null
+++ b/doc/zh/docs/model_zoo/imagenet/inception/README.md
@@ -0,0 +1,36 @@
+name: Inception V4 on ImageNet SINGA version: 1.1.1 SINGA commit: 
parameter_url: 
https://s3-ap-southeast-1.amazonaws.com/dlfile/inception_v4.tar.gz 
parameter_sha1: 5fdd6f5d8af8fd10e7321d9b38bb87ef14e80d56 license: 
https://github.com/tensorflow/models/tree/master/slim
+
+---
+
+# 用Inception V4做图像分类
+
+
+这个例子中,我们将Tensorflow训练好的Inception 
V4转换为SINGA模型以用作图像分类。
+
+## 操作说明
+
+* 下载参数的checkpoint文件到如下目录
+
+        $ wget
+               $ tar xvf inception_v4.tar.gz
+
+* 运行程序
+
+        # use cpu
+        $ python serve.py -C &
+        # use gpu
+        $ python serve.py &
+
+* 提交图片进行分类
+
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+
+image1.jpg, image2.jpg和image3.jpg应该在执行指令前就已被下载。
+
+## 详细信息
+
+我们首å…
ˆä»ŽTensorflow的checkpoint文件中提取参数值到一个pickle版本中。 
下载并解压缩checkpoint文件后,运行以下脚本
+
+       $ python convert.py --file_name=inception_v4.ckpt
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/imagenet/resnet/README.md
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/imagenet/resnet/README.md 
b/doc/zh/docs/model_zoo/imagenet/resnet/README.md
new file mode 100644
index 0000000..b790b61
--- /dev/null
+++ b/doc/zh/docs/model_zoo/imagenet/resnet/README.md
@@ -0,0 +1,50 @@
+name: Resnets on ImageNet SINGA version: 1.1 SINGA commit: 
45ec92d8ffc1fa1385a9307fdf07e21da939ee2f parameter_url: 
https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-18.tar.gz license: 
Apache V2, https://github.com/facebook/fb.resnet.torch/blob/master/LICENSE
+
+---
+
+# 用ResNet做图像分类
+
+
+这个例子中,我们将Torch训练好的ResNet转换为SINGA模型以用作图像分类。
+
+## 操作说明
+
+* 下载参数的checkpoint文件到如下目录
+
+        $ wget 
https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-18.tar.gz
+               $ wget 
https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/synset_words.txt
+               $ tar xvf resnet-18.tar.gz
+
+* 运行程序
+
+        $ python serve.py -h
+               
+* 运行程序
+
+        # use cpu
+               $ python serve.py --use_cpu --parameter_file resnet-18.pickle 
--model resnet --depth 18 &
+               # use gpu
+               $ python serve.py --parameter_file resnet-18.pickle --model 
resnet --depth 18 &
+
+       我们提供了以下模型和深度配置的参数文件:
+       * resnet (原始 resnet), 
[18](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-18.tar.gz)|[34](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-34.tar.gz)|[101](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-101.tar.gz)|[152](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-152.tar.gz)
+       * 包括批量正则, 
[50](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-50.tar.gz)
+       * wrn (宽 resnet), 
[50](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/wrn-50-2.tar.gz)
+       * preact (包括 pre-activation 的 resnet) 
[200](https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/resnet-200.tar.gz)
+
+
+* 提交图片进行分类
+
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+
+image1.jpg, image2.jpg和image3.jpg应该在执行指令前就已被下载。
+
+## 详细信息
+
+用`convert.py`从torch参数文件中提取参数值
+
+* 运行程序
+
+       $ python convert.py -h
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/imagenet/vgg/README.md
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/imagenet/vgg/README.md 
b/doc/zh/docs/model_zoo/imagenet/vgg/README.md
new file mode 100644
index 0000000..083bf8b
--- /dev/null
+++ b/doc/zh/docs/model_zoo/imagenet/vgg/README.md
@@ -0,0 +1,48 @@
+name: VGG on ImageNet SINGA version: 1.1.1 SINGA commit: license: 
https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
+
+---
+
+# 用VGG做图像分类
+
+
+这个例子中,我们将PyTorch训练好的VGG转换为SINGA模型以用作图像分类。
+
+## 操作说明
+
+* 下载参数的checkpoint文件到如下目录
+
+        $ wget https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg11.tar.gz
+               $ wget 
https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/synset_words.txt
+               $ tar xvf vgg11.tar.gz
+
+* 运行程序
+
+        $ python serve.py -h
+               
+* 例子
+
+        # use cpu
+               $ python serve.py --use_cpu --parameter_file vgg11.pickle 
--depth 11 &
+               # use gpu
+               $ python serve.py --parameter_file vgg11.pickle --depth 11 &
+
+       我们提供了以下模型和深度配置的参数文件:
+       * 不使用批量正则, 
[11](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg11.tar.gz), 
[13](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg13.tar.gz), 
[16](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg16.tar.gz), 
[19](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg19.tar.gz)
+       * 使用批量正则, 
[11](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg11_bn.tar.gz), 
[13](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg13_bn.tar.gz), 
[16](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg16_bn.tar.gz), 
[19](https://s3-ap-southeast-1.amazonaws.com/dlfile/vgg/vgg19_bn.tar.gz)
+               
+
+* 提交图片进行分类
+
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+        $ curl -i -F [email protected] http://localhost:9999/api
+
+image1.jpg, image2.jpg和image3.jpg应该在执行指令前就已被下载。
+
+## 详细信息
+
+用`convert.py`从Pytorch参数文件中提取参数值
+
+* 运行程序
+
+       $ python convert.py -h
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/index.rst
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/index.rst b/doc/zh/docs/model_zoo/index.rst
index 6ee60a8..75f0e27 100644
--- a/doc/zh/docs/model_zoo/index.rst
+++ b/doc/zh/docs/model_zoo/index.rst
@@ -23,7 +23,12 @@
 
    cifar10/README
    char-rnn/README
+   mnist/README
    imagenet/alexnet/README
+   imagenet/densenet/README
    imagenet/googlenet/README
+   imagenet/inception/README
+   imagenet/resnet/README
+   imagenet/vgg/README
 
 

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/doc/zh/docs/model_zoo/mnist/README.md
----------------------------------------------------------------------
diff --git a/doc/zh/docs/model_zoo/mnist/README.md 
b/doc/zh/docs/model_zoo/mnist/README.md
new file mode 100644
index 0000000..ba8e3f1
--- /dev/null
+++ b/doc/zh/docs/model_zoo/mnist/README.md
@@ -0,0 +1,18 @@
+# 在MNIST数据集上训练RBM模型
+
+这个例子使用MNIST数据集来训练一个RBM模型。RBM模型及其超
参数参考[Hinton的论文](http://www.cs.toronto.edu/~hinton/science.pdf)中的设定。
+
+
+## 操作说明
+
+* 
下载预处理的[MNIST数据集](https://github.com/mnielsen/neural-networks-and-deep-learning/raw/master/data/mnist.pkl.gz)。
+
+* 开始训练,
+
+        python train.py mnist.pkl.gz
+
+       默认情况下,训练代码将在CPU上运行。 
要在GPU卡上运行它,请使用附加参数启动程序,
+
+        python train.py mnist.pkl.gz --use_gpu
+
+

http://git-wip-us.apache.org/repos/asf/incubator-singa/blob/b235e9b6/examples/index.rst
----------------------------------------------------------------------
diff --git a/examples/index.rst b/examples/index.rst
index d08a557..fca66f9 100644
--- a/examples/index.rst
+++ b/examples/index.rst
@@ -23,7 +23,11 @@ Model Zoo
 
    cifar10/README
    char-rnn/README
+   mnist/README
    imagenet/alexnet/README
+   imagenet/densenet/README
    imagenet/googlenet/README
-
+   imagenet/inception/README
+   imagenet/resnet/README
+   imagenet/vgg/README
 

Reply via email to