技术栈

主页 > AI >

Machine Learning(一):基于 TensorFlow 实现宠物血统智能识别

技术栈 - 中国领先的IT技术门户
  • Hello TensorFlow
  • TensorFlow C library
  • TensorFlow Go bingding

Hello TensorFlow

人类喜欢将所有事物都纳入鄙视链的范畴,宠物当然也不例外。一般来说,拥有一只纯种宠物可以让主人占据鄙视链的云端,进而鄙视那些混血或者流浪宠物。甚至还发展出了专业的鉴定机构,可以颁发《血统证明书》。但是考究各类纯种鉴定的常规方法:例如眼睛的大小、颜色、鼻子的特点、身躯长度、尾巴特征、毛发等,当然也包括一些比较玄幻的特征:宠物家族的个性、气质等等。抛开“黑魔法”不在此讨论之外,既然是基于生物外形特征鉴定,判断是否纯种的需求本质上就是一个图像识别服务。

Tensorflow is not a Machine Learning specific library, instead, is a general purpose computation library that represents computations with graphs.

TensorFlow 开源软件库(Apache 2.0 许可证),最初由 Google Brain 团队开发。TensorFlow 提供了一系列算法模型和编程接口,让我们可以快速构建一个基于机器学习的智能服务。对于开发者来说,目前有四种编程接口可供选择:

  • C++ source code: Tensorflow 核心基于 C++ 编写,支持从高到低各个层级的操作;
  • Python bindings & Python library: 对标 C++ 实现,支持 Python 调用 C++ 函数;
  • Java bindings;
  • Go binding;

下面是一个简单的实例:

[图片上传失败...(image-8754c1-1518459129749)]

环境准备

  • 安装 TensorFlow C library,包含一个头文件 c_api.h 和 libtensorflow.so
wget https://storage.googleapis.com/tensorflow/libtensorflow/libtensorflow-cpu-linux-x86_64-1.5.0.tar.gz

## options
TF_TYPE="cpu" # Change to "gpu" for GPU support
TF_VERSION='1.5.0'
curl -L 
  "https://storage.googleapis.com/tensorflow/libtensorflow/libtensorflow-${TF_TYPE}-$(go env GOOS)-x86_64-${TF_VERSION}.tar.gz" |
go get github.com/tensorflow/tensorflow/tensorflow/go
go get github.com/tensorflow/tensorflow/tensorflow/go/op
  • 下载模型(demo model),包含一个标签文件 label_strings.txt 和 graph.pb
mkdir model
wget https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip -O model/inception.zip
unzip model/inception.zip -d model
chmod -R 777 model

Tensorflow Model Function

//Loading TensorFlow model
func loadModel() error {
  // Load inception model
  model, err := ioutil.ReadFile("./model/tensorflow_inception_graph.pb")
  if err != nil {
    return err
  }
  graph = tf.NewGraph()
  if err := graph.Import(model, ""); err != nil {
    return err
  }
  // Load labels
  labelsFile, err := os.Open("./model/imagenet_comp_graph_label_strings.txt")
  if err != nil {
    return err
  }
  defer labelsFile.Close()
  scanner := bufio.NewScanner(labelsFile)
  // Labels are separated by newlines
  for scanner.Scan() {
    labels = append(labels, scanner.Text())
  }
  if err := scanner.Err(); err != nil {
    return err
  }
  return nil
}

Classifying Workflow

基于 Tensorflow 模型实现图像识别的主要流程如下:

  • 图像转换 (Convert to tensor )
  • 图像标准化( Normalize )
  • 图像分类 ( Classifying )
func recognizeHandler(w http.ResponseWriter, r *http.Request, _ httprouter.Params) {
  // Read image
  imageFile, header, err := r.FormFile("image")
  // Will contain filename and extension
  imageName := strings.Split(header.Filename, ".")
  if err != nil {
    responseError(w, "Could not read image", http.StatusBadRequest)
    return
  }
  defer imageFile.Close()
  var imageBuffer bytes.Buffer
  // Copy image data to a buffer
  io.Copy(&imageBuffer, imageFile)

  // ...

  tensor, err := makeTensorFromImage(&imageBuffer, imageName[:1][0])
  if err != nil {
    responseError(w, "Invalid image", http.StatusBadRequest)
    return
  }

  // ...
}

函数 makeTensorFromImage() which runs an image tensor through the normalization graph.

func makeTensorFromImage(imageBuffer *bytes.Buffer, imageFormat string) (*tf.Tensor, error) {
  tensor, err := tf.NewTensor(imageBuffer.String())
  if err != nil {
    return nil, err
  }
  graph, input, output, err := makeTransformImageGraph(imageFormat)
  if err != nil {
    return nil, err
  }
  session, err := tf.NewSession(graph, nil)
  if err != nil {
    return nil, err
  }
  defer session.Close()
  normalized, err := session.Run(
    map[tf.Output]*tf.Tensor{input: tensor},
    []tf.Output{output},
    nil)
  if err != nil {
    return nil, err
  }
  return normalized[0], nil
}

函数 maketransformimagegraph() 将图形的像素值调整到 224x224,以符合模型输入参数要求。

func makeTransformImageGraph(imageFormat string) (graph *tf.Graph, input, output tf.Output, err error) {
  const (
    H, W  = 224, 224
    Mean  = float32(117)
    Scale = float32(1)
  )
  s := op.NewScope()
  input = op.Placeholder(s, tf.String)
  // Decode PNG or JPEG
  var decode tf.Output
  if imageFormat == "png" {
    decode = op.DecodePng(s, input, op.DecodePngChannels(3))
  } else {
    decode = op.DecodeJpeg(s, input, op.DecodeJpegChannels(3))
  }
  // Div and Sub perform (value-Mean)/Scale for each pixel
  output = op.Div(s,
    op.Sub(s,
      // Resize to 224x224 with bilinear interpolation
      op.ResizeBilinear(s,
        // Create a batch containing a single image
        op.ExpandDims(s,
          // Use decoded pixel values
          op.Cast(s, decode, tf.Float),
          op.Const(s.SubScope("make_batch"), int32(0))),
        op.Const(s.SubScope("size"), []int32{H, W})),
      op.Const(s.SubScope("mean"), Mean)),
    op.Const(s.SubScope("scale"), Scale))
  graph, err = s.Finalize()
  return graph, input, output, err
}

最后,将格式化的 image tensor 输入到 Inception model graph 中运算。

session, err := tf.NewSession(graph, nil)
if err != nil {
  log.Fatal(err)
}
defer session.Close()
output, err := session.Run(
  map[tf.Output]*tf.Tensor{
    graph.Operation("input").Output(0): tensor,
  },
  []tf.Output{
    graph.Operation("output").Output(0),
  },
  nil)
if err != nil {
  responseError(w, "Could not run inference", http.StatusInternalServerError)
  return
}

Testing

func main() {
  if err := loadModel(); err != nil {
    log.Fatal(err)
    return
  }
  r := httprouter.New()
  r.POST("/recognize", recognizeHandler)
  err := http.ListenAndServe(":8080", r)
  if err != nil {
    log.Println(err)
    return
  }
}
$ curl localhost:8080/recognize -F 'image=@../data/IMG_3560.png'
{
  "filename":"IMG_3000.png",
  "labels":[
    {"label":"black swan","probability":0.98746836,"Percent":"98.75%"},
    {"label":"oystercatcher","probability":0.0040768473,"Percent":"0.41%"},
    {"label":"American coot","probability":0.002185003,"Percent":"0.22%"},
    {"label":"black stork","probability":0.0011524856,"Percent":"0.12%"},
    {"label":"redshank","probability":0.0010183558,"Percent":"0.10%"}]
}

通过上面的案例我们可以发现,这个服务目前可以对于黑天鹅图像的推算概率值为 98.75%,非常准确;但是对于另外两张宠物狗的图像,最高的推算概率值也仅有 30% 左右,虽然也没有被识别成猫咪或者狼,但是和理想效果要求可用性还有一段距离(此处暂时忽略物种本身的复杂性)。主要是因为现在我们使用的还只是一个非常“原始”的模型,如果需要为小众领域服务(宠物,也可以是其它事物),需要通过训练(Training Models)增强优化,或者引入更丰富的标签,更合适的模型。当然,训练过程中也会存在样本质量不佳的情况,错误样本和各种噪音也会影响准确度。

扩展阅读

We know that label 866 (military uniform) should be the top label for the Admiral Hopper image.

参考文献

责任编辑:admin  二维码分享:
本文标签: errnilopreturntfgraph