【发布时间】：2021-01-10 20:16:42
【问题描述】：
我正在尝试为 yolo 对象检测制作一个自动注释工具，它使用预先训练的模型来查找检测结果，我设法整理了一些代码，但我有点卡住了，据我所知，这需要YOLO的注解格式：
18 0.154167 0.431250 0.091667 0.612500
我得到了我的代码
0.5576068858305613, 0.5410404056310654, -0.7516528169314066, 0.33822181820869446
我不知道为什么我在第三个数字上得到-，如果我需要缩短我的浮点数，
如果有人可以帮助我，我将在下面发布代码，完成此项目后，如果有人想使用它，我将发布整个代码
def convert(size, box):
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x,y,w,h)
以上代码是将坐标转换为YOLO格式的函数，对于大小需要传递(w,h)，对于框需要传递(x,x+w, y, y+ h)
net = cv2.dnn.readNetFromDarknet(config_path, weights_path)
# path_name = "images/city_scene.jpg"
path_name = image
image = cv2.imread(path_name)
file_name = os.path.basename(path_name)
filename, ext = file_name.split(".")
h, w = image.shape[:2]
# create 4D blob
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416), swapRB=True, crop=False)
# sets the blob as the input of the network
net.setInput(blob)
# get all the layer names
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# feed forward (inference) and get the network output
# measure how much it took in seconds
start = time.perf_counter()
layer_outputs = net.forward(ln)
time_took = time.perf_counter() - start
print(f"Time took: {time_took:.2f}s")
boxes, confidences, class_ids = [], [], []
b=[]
a=[]
# loop over each of the layer outputs
for output in layer_outputs:
# loop over each of the object detections
for detection in output:
# extract the class id (label) and confidence (as a probability) of
# the current object detection
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
# discard weak predictions by ensuring the detected
# probability is greater than the minimum probability
if confidence > CONFIDENCE:
# scale the bounding box coordinates back relative to the
# size of the image, keeping in mind that YOLO actually
# returns the center (x, y)-coordinates of the bounding
# box followed by the boxes' width and height
box = detection[0:4] * np.array([w, h, w, h])
(centerX, centerY, width, height) = box.astype("float")
# use the center (x, y)-coordinates to derive the top and
# and left corner of the bounding box
x = int(centerX - (width / 2))
y = int(centerY - (height / 2))
a = w, h
convert(a, box)
boxes.append([x, y, int(width), int(height)])
confidences.append(float(confidence))
class_ids.append(class_id)
idxs = cv2.dnn.NMSBoxes(boxes, confidences, SCORE_THRESHOLD,
IOU_THRESHOLD)
font_scale = 1
thickness = 1
# ensure at least one detection exists
if len(idxs) > 0:
# loop over the indexes we are keeping
for i in idxs.flatten():
# extract the bounding box coordinates
x, y = boxes[i][0], boxes[i][1]
w, h = boxes[i][2], boxes[i][3]
# draw a bounding box rectangle and label on the image
color = [int(c) for c in colors[class_ids[i]]]
ba=w,h
print(w,h)
cv2.rectangle(image, (x, y), (x + w, y + h), color=color, thickness=thickness)
text = "{}".format(labels[class_ids[i]])
conf = "{:.3f}".format(confidences[i], x, y)
int1, int2 = (x, y)
print(text)
#print(convert(ba, box))
#b=w,h
#print(convert(b, boxes))
#print(convert(a, box)) #coordinates
ivan = str(int1)
b.append([text, ivan])
#a.append(float(conf))
#print(a)
# calculate text width & height to draw the transparent boxes as background of the text
(text_width, text_height) = \
cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, fontScale=font_scale, thickness=thickness)[0]
text_offset_x = x
text_offset_y = y - 5
box_coords = ((text_offset_x, text_offset_y), (text_offset_x + text_width + 2, text_offset_y - text_height))
overlay = image.copy()
cv2.rectangle(overlay, box_coords[0], box_coords[1], color=color, thickness=cv2.FILLED)
# add opacity (transparency to the box)
image = cv2.addWeighted(overlay, 0.6, image, 0.4, 0)
# now put the text (label: confidence %)
cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX,
fontScale=font_scale, color=(0, 0, 0), thickness=thickness)
text = "{}".format(labels[class_ids[i]],x,y)
conf = "{:.3f}".format(confidences[i])
【问题讨论】：