终于有点时间，可以写继续写notes，这样可以让整个学习过程的印象更加深入。

本节课为CNN的第三周，总的来说就是讲述如何通过pre-train的物体模型，识别整张照片上的物体。和以往前两周的课程一样，围绕着若干篇论文算法展开 Detecting Algorithm

• Object Localization
• Landmark Detection, which describe less in the class about how to detect the interal features of an object by key landmarks
• Object Detection, talking about how to detect an object with bounding box
• Sliding Window

这里主要重点回顾YOLO（you only look once）。这是本课重点阐述的内容，video有两个，作业也是直接就是讲述YOLO，顺带一点其他算法。

• 起点，将原图划分成19x19的区块 （方便简化计算）
• Input image (608, 608, 3)
• The input image goes through a CNN, resulting in a (19,19,5,85) dimensional output.
• After flattening the last two dimensions, the output is a volume of shape (19, 19, 425):
  • Each cell in a 19x19 grid over the input image gives 425 numbers.
  • 425 = 5 x 85 because each cell contains predictions for 5 boxes, corresponding to 5 anchor boxes, as seen in lecture.
  • 85 = 5 + 80 where 5 is because (pc,bx,by,bh,bw)(pc,bx,by,bh,bw) has 5 numbers, and and 80 is the number of classes we’d like to detect
• You then select only few boxes based on:
  • Score-thresholding: throw away boxes that have detected a class with a score less than the threshold
  • Non-max suppression: Compute the Intersection over Union and avoid selecting overlapping boxes
• This gives you YOLO’s final output.

What you should remember:

• YOLO is a state-of-the-art object detection model that is fast and accurate
• It runs an input image through a CNN which outputs a 19x19x5x85 dimensional volume.
• The encoding can be seen as a grid where each of the 19x19 cells contains information about 5 boxes.
• You filter through all the boxes using non-max suppression. Specifically:
  • Score thresholding on the probability of detecting a class to keep only accurate (high probability) boxes
  • Intersection over Union (IoU) thresholding to eliminate overlapping boxes
• Because training a YOLO model from randomly initialized weights is non-trivial and requires a large dataset as well as lot of computation, we used previously trained model parameters in this exercise. If you wish, you can also try fine-tuning the YOLO model with your own dataset, though this would be a fairly non-trivial exercise.

最近已经学到了机器学习的第四课CNN的部分。这个部分里面还是用到了一些Tensorflow的基本内容。这里把一些简单的方法做个总结，以做备忘，也许之后用得上。

1
2

# Use tf.image.non_max_suppression() to get the list of indices corresponding to boxes you keep
   nms_indices = tf.image.non_max_suppression(boxes, scores, max_boxes, iou_threshold)

对于TF的Run始终觉得需要系统的理解一下

1
2
3
4

# Run the session with the correct tensors and choose the correct placeholders in the feed_dict.
    # You'll need to use feed_dict={yolo_model.input: ... , K.learning_phase(): 0})
    out_scores, out_boxes, out_classes = sess.run([scores, boxes, classes],
                                                  feed_dict={yolo_model.input: image_data, K.learning_phase(): 0})

这里除了TensorFlow还得多提一个Keras，一个构建在TF上面更加丰富函数的第三方包

1
2

keras.backend.argmax(x, axis=-1)
keras.backend.max(x, axis=None, keepdims=False)

np也有一些特殊的方法，比较不常见和不容易理解，下面np.eye就是把一个Y变成C个为一组的one-hot

1
2
3

def convert_to_one_hot(Y, C):
    Y = np.eye(C)[Y.reshape(-1)]
    return Y