YOLO演算法詳細解析（一）

# Preprocess your image
image, image_data = preprocess_image("images/" + image_file, model_image_size = (608, 608))

# Run the session with the correct tensors and choose the correct placeholders in the feed_dict.
# Youll need to use feed_dict={yolo_model.input: ... , K.learning_phase(): 0})
### START CODE HERE ### (≈ 1 line)
out_scores, out_boxes, out_classes = sess.run([scores, boxes, classes], feed_dict={yolo_model.input: image_data,
input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0})
### END CODE HERE ###

# Print predictions info
print(Found {} boxes for {}.format(len(out_boxes), image_file))
# Generate colors for drawing bounding boxes.
colors = generate_colors(class_names)
# Draw bounding boxes on the image file
draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors)
# Save the predicted bounding box on the image
image.save(os.path.join("out", image_file), quality=90)
# Display the results in the notebook
output_image = scipy.misc.imread(os.path.join("out", image_file))
imshow(output_image)

# Scale boxes back to original image shape.
## 將boxes的坐標值按照image_shape的變換比例還原
height = image_shape[0]
width = image_shape[1]
## 講image_dims變成(4,)的張量
image_dims = K.stack([height, width, height, width])
image_dims = K.reshape(image_dims, [1, 4])

boxes = boxes * image_dims

# Use one of the functions youve implemented to perform Non-max suppression with a threshold of iou_threshold (≈1 line)
## yolo_non_max_suppression 函數上文中已有解析
scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes = max_boxes, iou_threshold = iou_threshold)

## 這裡返回的值是[y,x,y,x]的組合
return K.concatenate([
box_mins[..., 1:2], # y_min
box_mins[..., 0:1], # x_min
box_maxes[..., 1:2], # y_max
box_maxes[..., 0:1] # x_max
])

# Reshape to batch, height, width, num_anchors, box_params.
anchors_tensor = K.reshape(K.variable(anchors), [1, 1, 1, num_anchors, 2])

# 取第2、3維 即19*19
conv_dims = K.shape(feats)[1:3] #conv_dims變成2維 每個維度19個值

# In YOLO the height index is the inner most iteration. [0,1,2,3,4,5,...,18]
conv_height_index = K.arange(0, stop=conv_dims[0])
conv_width_index = K.arange(0, stop=conv_dims[1])
#tile(x, n)函數 將x在各個維度上重複n次，x為張量，n為與x維度數目相同的列表 這裡conv_heifh_index只有一維
# 下面這部分看著很繞 但實際上是獲得(1,19,19,1,2)維度的位移表
conv_height_index = K.tile(conv_height_index, [conv_dims[1]])
conv_width_index = K.tile(K.expand_dims(conv_width_index, 0), [conv_dims[0], 1])
conv_width_index = K.flatten(K.transpose(conv_width_index))
conv_index = K.transpose(K.stack([conv_height_index, conv_width_index]))
conv_index = K.reshape(conv_index, [1, conv_dims[0], conv_dims[1], 1, 2])
conv_index = K.cast(conv_index, K.dtype(feats)

feats = K.reshape(feats, [-1, conv_dims[0], conv_dims[1], num_anchors, num_classes + 5])
conv_dims = K.cast(K.reshape(conv_dims, [1, 1, 1, 1, 2]), K.dtype(feats))

# Static generation of conv_index: 這種靜態方法更容易理解一些
# conv_index = np.array([_ for _ in np.ndindex(conv_width, conv_height)])
# conv_index = conv_index[:, [1, 0]] # swap columns for YOLO ordering.
# conv_index = K.variable(
# conv_index.reshape(1, conv_height, conv_width, 1, 2))
# feats = Reshape(
# (conv_dims[0], conv_dims[1], num_anchors, num_classes + 5))(feats)

box_confidence = K.sigmoid(feats[..., 4:5])
box_xy = K.sigmoid(feats[..., :2])

box_wh = K.exp(feats[..., 2:4])
box_class_probs = K.softmax(feats[..., 5:])

#box_xy 是圖片通過model的預測得出的可能是object的85位值中的第1-2位值 代表的是物體被預測的中心位置
#box_wh 是圖片通過model的預測得出的object的寬度和高度 再乘以對應的anchors_tensor之後 按照anchors的形狀等比例放大

# conv_index 對應的grid cell格子數（從左和從上數的位移）
box_xy = (box_xy + conv_index) / conv_dims

#在這裡+conv_index是為了找到對應的cell 將圖片的中心落於預測的cell中 得到相對於整張圖片的box_xy

box_wh = box_wh * anchors_tensor / conv_dims