【官方教程】TensorFlow在图像识别中的应用

cd tensorflow/models/image/imagenet

python classify_image.py

giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca (score = 0.88493)
indri, indris, Indri indri, Indri brevicaudatus (score = 0.00878)
lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens (score = 0.00317)
custard apple (score = 0.00149)
earthstar (score = 0.00127)

wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip -O tensorflow/examples/label_image/data/inception_dec_2015.zip

unzip tensorflow/examples/label_image/data/inception_dec_2015.zip -d tensorflow/examples/label_image/data/

bazel build tensorflow/examples/label_image/...

bazel-bin/tensorflow/examples/label_image/label_image

I tensorflow/examples/label_image/main.cc:200] military uniform (866): 0.647296
I tensorflow/examples/label_image/main.cc:200] suit (794): 0.0477196
I tensorflow/examples/label_image/main.cc:200] academic gown (896): 0.0232411
I tensorflow/examples/label_image/main.cc:200] bow tie (817): 0.0157356
I tensorflow/examples/label_image/main.cc:200] bolo tie (940): 0.0145024

bazel-bin/tensorflow/examples/label_image/label_image --image=my_image.png

// Given an image file name, read in the data, try to decode it as an image,
// resize it to the requested size, and then scale the values as desired.
Status ReadTensorFromImageFile(string file_name, const int input_height,
                               const int input_width, const float input_mean,
                               const float input_std,
                               std::vector<Tensor>* out_tensors) {
  tensorflow::GraphDefBuilder b;

  string input_name = "file_reader";
  string output_name = "normalized";
  tensorflow::Node* file_reader =
      tensorflow::ops::ReadFile(tensorflow::ops::Const(file_name, b.opts()),
                                b.opts().WithName(input_name));

  // Now try to figure out what kind of file it is and decode it.
  const int wanted_channels = 3;
  tensorflow::Node* image_reader;
  if (tensorflow::StringPiece(file_name).ends_with(".png")) {
    image_reader = tensorflow::ops::DecodePng(
        file_reader,
        b.opts().WithAttr("channels", wanted_channels).WithName("png_reader"));
  } else {
    // Assume if it's not a PNG then it must be a JPEG.
    image_reader = tensorflow::ops::DecodeJpeg(
        file_reader,
        b.opts().WithAttr("channels", wanted_channels).WithName("jpeg_reader"));
  }
  // Now cast the image data to float so we can do normal math on it.
  tensorflow::Node* float_caster = tensorflow::ops::Cast(
      image_reader, tensorflow::DT_FLOAT, b.opts().WithName("float_caster"));
  // The convention for image ops in TensorFlow is that all images are expected
  // to be in batches, so that they're four-dimensional arrays with indices of
  // [batch, height, width, channel]. Because we only have a single image, we
  // have to add a batch dimension of 1 to the start with ExpandDims().
  tensorflow::Node* dims_expander = tensorflow::ops::ExpandDims(
      float_caster, tensorflow::ops::Const(0, b.opts()), b.opts());
  // Bilinearly resize the image to fit the required dimensions.
  tensorflow::Node* resized = tensorflow::ops::ResizeBilinear(
      dims_expander, tensorflow::ops::Const({input_height, input_width},
                                            b.opts().WithName("size")),
      b.opts());
  // Subtract the mean and divide by the scale.
  tensorflow::ops::Div(
      tensorflow::ops::Sub(
          resized, tensorflow::ops::Const({input_mean}, b.opts()), b.opts()),
      tensorflow::ops::Const({input_std}, b.opts()),
      b.opts().WithName(output_name));

  // This runs the GraphDef network definition that we've just constructed, and
  // returns the results in the output tensor.
  tensorflow::GraphDef graph;
  TF_RETURN_IF_ERROR(b.ToGraphDef(&graph));

  std::unique_ptr<tensorflow::Session> session(
      tensorflow::NewSession(tensorflow::SessionOptions()));
  TF_RETURN_IF_ERROR(session->Create(graph));
  TF_RETURN_IF_ERROR(session->Run({}, {output_name}, {}, out_tensors));
  return Status::OK();

// Reads a model graph definition from disk, and creates a session object you
// can use to run it.
Status LoadGraph(string graph_file_name,
                 std::unique_ptr<tensorflow::Session>* session) {
  tensorflow::GraphDef graph_def;
  Status load_graph_status =
      ReadBinaryProto(tensorflow::Env::Default(), graph_file_name, &graph_def);
  if (!load_graph_status.ok()) {
    return tensorflow::errors::NotFound("Failed to load compute graph at '",
                                        graph_file_name, "'");
  }

  session->reset(tensorflow::NewSession(tensorflow::SessionOptions()));
  Status session_create_status = (*session)->Create(graph_def);
  if (!session_create_status.ok()) {
    return session_create_status;
  }
  return Status::OK();
}

// Analyzes the output of the Inception graph to retrieve the highest scores and
// their positions in the tensor, which correspond to categories.
Status GetTopLabels(const std::vector<Tensor>& outputs, int how_many_labels,
                    Tensor* indices, Tensor* scores) {
  tensorflow::GraphDefBuilder b;
  string output_name = "top_k";
  tensorflow::ops::TopK(tensorflow::ops::Const(outputs[0], b.opts()),
                        how_many_labels, b.opts().WithName(output_name));
  // This runs the GraphDef network definition that we've just constructed, and
  // returns the results in the output tensors.
  tensorflow::GraphDef graph;
  TF_RETURN_IF_ERROR(b.ToGraphDef(&graph));
  std::unique_ptr<tensorflow::Session> session(
      tensorflow::NewSession(tensorflow::SessionOptions()));
  TF_RETURN_IF_ERROR(session->Create(graph));
  // The TopK node returns two outputs, the scores and their original indices,
  // so we have to append :0 and :1 to specify them both.
  std::vector<Tensor> out_tensors;
  TF_RETURN_IF_ERROR(session->Run({}, {output_name + ":0", output_name + ":1"},
                                  {}, &out_tensors));
  *scores = out_tensors[0];
  *indices = out_tensors[1];
  return Status::OK();

int main(int argc, char* argv[]) {
  // We need to call this to set up global state for TensorFlow.
  tensorflow::port::InitMain(argv[0], &argc, &argv);
  Status s = tensorflow::ParseCommandLineFlags(&argc, argv);
  if (!s.ok()) {
    LOG(ERROR) << "Error parsing command line flags: " << s.ToString();
    return -1;
  }

  // First we load and initialize the model.
  std::unique_ptr<tensorflow::Session> session;
  string graph_path = tensorflow::io::JoinPath(FLAGS_root_dir, FLAGS_graph);
  Status load_graph_status = LoadGraph(graph_path, &session);
  if (!load_graph_status.ok()) {
    LOG(ERROR) << load_graph_status;
    return -1;
  }

  // Get the image from disk as a float array of numbers, resized and normalized
  // to the specifications the main graph expects.
  std::vector<Tensor> resized_tensors;
  string image_path = tensorflow::io::JoinPath(FLAGS_root_dir, FLAGS_image);
  Status read_tensor_status = ReadTensorFromImageFile(
      image_path, FLAGS_input_height, FLAGS_input_width, FLAGS_input_mean,
      FLAGS_input_std, &resized_tensors);
  if (!read_tensor_status.ok()) {
    LOG(ERROR) << read_tensor_status;
    return -1;
  }
  const Tensor& resized_tensor = resized_tensors[0];

  // Actually run the image through the model.
  std::vector<Tensor> outputs;
  Status run_status = session->Run({{FLAGS_input_layer, resized_tensor}},
                                   {FLAGS_output_layer}, {}, &outputs);
  if (!run_status.ok()) {
    LOG(ERROR) << "Running model failed: " << run_status;
    return -1;
  }

  // This is for automated testing to make sure we get the expected result with
  // the default settings. We know that label 866 (military uniform) should be
  // the top label for the Admiral Hopper image.
  if (FLAGS_self_test) {
    bool expected_matches;
    Status check_status = CheckTopLabel(outputs, 866, &expected_matches);
    if (!check_status.ok()) {
      LOG(ERROR) << "Running check failed: " << check_status;
      return -1;
    }
    if (!expected_matches) {
      LOG(ERROR) << "Self-test failed!";
      return -1;
    }
  }

  // Do something interesting with the results we've generated.
  Status print_status = PrintTopLabels(outputs, FLAGS_labels);

  if (!print_status.ok()) {
    LOG(ERROR) << "Running print failed: " << print_status;
    return -1;
  }