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|34|101|152
包括批量正则, 50
wrn (宽 resnet), 50
preact (包括 pre-activation 的 resnet) 200

提交图片进行分类

  $ curl -i -F image=@image1.jpg http://localhost:9999/api
  $ curl -i -F image=@image2.jpg http://localhost:9999/api
  $ curl -i -F image=@image3.jpg 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
```