Object 使用 YOLO 检测：获取每个检测到的 object 的计数

Question

I am using YOLO to identify objects which is working fine however, I want to get count of the vehicles identified and to apply some calc_pollution further. I am using below code however, I am getting error: TypeError: list indices must be integers or slices, not tuple for the line: L = [labels.get(value) for index,value in enumerate(v_labels[0]) if v_scores[0,index] > 0.1]

# correct the sizes of the bounding boxes for the shape of the image
correct_yolo_boxes(boxes, image_h, image_w, input_h, input_w)
# suppress non-maximal boxes
do_nms(boxes, 0.5)
# define the labels
labels = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck",
    "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench",
    "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe"]
# get the details of the detected objects
v_boxes, v_labels, v_scores = get_boxes(boxes, labels, class_threshold)
# summarize what we found
for i in range(len(v_boxes)):
    print(v_labels[i], v_scores[i])
# draw what we found
draw_boxes(photo_filename, v_boxes, v_labels, v_scores)
# Filtering results
L = [labels.get(value) for index,value in enumerate(v_labels[0]) if v_scores[0,index] > 0.1]
M=[]
vehicles=['car','bus','truck','motorcycle','auto-rickshaw']
for i in L:
  if i['name']in vehicles:
    M.append(i['name'])
S=set(M)
text=''
car=motorcycle=truck=bus=auto_rickshaw=0
for i in S:
  if i == 'car': car += M.count(i)
  if i == 'motorcycle': motorcycle += M.count(i)
  if i == 'truck': truck += M.count(i)
  if i == 'bus': bus += M.count(i)
  if i == 'auto-rickshaw' : auto_rickshaw += M.count(i)
  text+=str(i +' : '+ str(M.count(i))+"\t" )
print('Vehicles Identified -',text)
calc_pollution(car, motorcycle, truck, bus, auto_rickshaw)

Any help would be appreciated.

Answer 1

Is v_scores a list of nested lists? Is so, you would need to change this part v_scores[0,index] to something like v_scores[0][index]

If that doesn't work, please share more information about the contents of v_boxes, v_labels, and v_scores.