【教程】OpenCV—Node.js教程系列：用Tensorflow和Caffe“做游戏”

// replace with path where you unzipped inception model
const inceptionModelPath = '../data/dnn/tf-inception'

const modelFile = path.resolve(inceptionModelPath, 'tensorflow_inception_graph.pb
');
const classNamesFile = path.resolve(inceptionModelPath, 'imagenet_comp_graph_
label_strings.txt');
if (!fs.existsSync(modelFile) || !fs.existsSync(classNamesFile)) {
  console.log('exiting: could not find inception model');
  console.log('download the model from: https://storage.googleapis.com/download.
tensorflow.org/models/inception5h.zip');
  return;
}

// read classNames and store them in an array
const classNames = fs.readFileSync(classNamesFile).toString().split("n");

// initialize tensorflow inception model from modelFile
const net = cv.readNetFromTensorflow(modelFile);

const classifyImg = (img) => {
  // inception model works with 224 x 224 images, so we resize
  // our input images and pad the image with white pixels to
  // make the images have the same width and height
  const maxImgDim = 224;
  const white = new cv.Vec(255, 255, 255);
  const imgResized = img.resizeToMax(maxImgDim).padToSquare(white);

  // network accepts blobs as input
  const inputBlob = cv.blobFromImage(imgResized);
  net.setInput(inputBlob);

  // forward pass input through entire network, will return
  // classification result as 1xN Mat with confidences of each class
  const outputBlob = net.forward();

  // find all labels with a minimum confidence
  const minConfidence = 0.05;
  const locations =
    outputBlob
      .threshold(minConfidence, 1, cv.THRESH_BINARY)
      .convertTo(cv.CV_8U)
      .findNonZero();

  const result =
    locations.map(pt => ({
      confidence: parseInt(outputBlob.at(0, pt.x) * 100) / 100,
      className: classNames[pt.x]
    }))
      // sort result by confidence
      .sort((r0, r1) => r1.confidence - r0.confidence)
      .map(res => `${res.className} (${res.confidence})`);

  return result;
}

const testData = [
  {
    image: '../data/banana.jpg',
    label: 'banana'
  },
  {
    image: '../data/husky.jpg',
    label: 'husky'
  },
  {
    image: '../data/car.jpeg',
    label: 'car'
  },
  {
    image: '../data/lenna.png',
    label: 'lenna'
  }
];

testData.forEach((data) => {
  const img = cv.imread(data.image);
  console.log('%s: ', data.label);
  const predictions = classifyImg(img);
  predictions.forEach(p => console.log(p));
  console.log();

  cv.imshowWait('img', img);
});

banana:
banana (0.95)
husky:
Siberian husky (0.78)
Eskimo dog (0.21)
car:
sports car (0.57)
racer (0.12)
lenna:
sombrero (0.34)
cowboy hat (0.3)

// replace with path where you unzipped inception model
const ssdcocoModelPath = '../data/dnn/coco-SSD_300x300'

const prototxt = path.resolve(ssdcocoModelPath, 'deploy.prototxt');
const modelFile = path.resolve(ssdcocoModelPath, 'VGG_coco_SSD_300x300_iter_40000
0.caffemodel');

if (!fs.existsSync(prototxt) || !fs.existsSync(modelFile)) {
  console.log('exiting: could not find ssdcoco model');
  console.log('download the model from: https://drive.google.com/file/d/0BzKzrI_
SkD1_dUY1Ml9GRTFpUWc/view');
  return;
}

// initialize ssdcoco model from prototxt and modelFile
const net = cv.readNetFromCaffe(prototxt, modelFile);

const classifyImg = (img) => {
  const white = new cv.Vec(255, 255, 255);
  // ssdcoco model works with 300 x 300 images
  const imgResized = img.resize(300, 300);

  // network accepts blobs as input
  const inputBlob = cv.blobFromImage(imgResized);
  net.setInput(inputBlob);

  // forward pass input through entire network, will return
  // classification result as 1x1xNxM Mat
  let outputBlob = net.forward();
  // extract NxM Mat
  outputBlob = outputBlob.flattenFloat(outputBlob.sizes[2], outputBlob.sizes[3]);

  const results = Array(outputBlob.rows).fill(0)
    .map((res, i) => {
      const className = classNames[outputBlob.at(i, 1)];
      const confidence = outputBlob.at(i, 2);
      const topLeft = new cv.Point(
        outputBlob.at(i, 3) * img.cols,
        outputBlob.at(i, 6) * img.rows
      );
      const bottomRight = new cv.Point(
        outputBlob.at(i, 5) * img.cols,
        outputBlob.at(i, 4) * img.rows
      );

      return ({
        className,
        confidence,
        topLeft,
        bottomRight
      })
    });

    return results;
};