我使用微小的yolo和暗网开发了我的自定义对象检测器。它工作得很好，但我需要一个特定的功能：网络输出边界框的每一个由类的数量+5个元素的矢量表示。前4个元素表示center_x、center_y、宽度和高度。第五个元素表示边界框包围对象的置信度。其余元素是与每个类(即对象类型(相关联的置信度。对于每个框，我需要每个类的置信度，但我在输出中只有最大置信度，其他的置信度输出为0。
示例运行：
打印(分数(返回
[0. 0. 0.5874982]
0.5874982是最大置信度。这是第三节课。但我不明白，因为其他人的信心是0。谢谢重播，我很抱歉我的英语不好。这是代码
import cv2 as cv
import argparse
import sys
import numpy as np
import os.path
confThreshold = 0.5
nmsThreshold = 0.6
inpWidth = 416 #Width of network's input image
inpHeight = 416 #Height of network's input image
parser = argparse.ArgumentParser(description='Object Detection using YOLO in OPENCV')
parser.add_argument('--image', help='Path to image file.')
parser.add_argument('--video', help='Path to video file.')
args = parser.parse_args()
# Load names of classes
classesFile = "obj.names"
classes = None
with open(classesFile, 'rt') as f:
classes = f.read().rstrip('n').split('n')
# Give the configuration and weight files for the model and load the network using them.
modelConfiguration = "yolov3-tiny-obj.cfg"
modelWeights = "pesi/pesi_3_classi_new/yolov3-tiny-obj_7050.weights"
net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
# Get the names of the output layers
def getOutputsNames(net):
layersNames = net.getLayerNames()
return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# Draw the predicted bounding box
def drawPred(classId, conf, left, top, right, bottom):
if classId==1:
cv.rectangle(frame, (left, top), (right, bottom), (3, 14, 186), 3)
elif classId==0:
cv.rectangle(frame, (left, top), (right, bottom), (40, 198, 31), 3)
elif classId==2:
cv.rectangle(frame, (left, top), (right, bottom), (40, 198, 31), 3)
label = '%.2f' % conf
# Get the label for the class name and its confidence
if classes:
assert(classId < len(classes))
label = '%s:%s' % (classes[classId], label)
#Display the label at the top of the bounding box
labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
top = max(top, labelSize[1])
cv.rectangle(frame, (left, top - round(1*labelSize[1])), (left + round(1*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.45, (0,0,0), 1)
# Remove the bounding boxes with low confidence using non-maxima suppression
def postprocess(frame, outs):
frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
# Scan through all the bounding boxes output from the network and keep only the
# ones with high confidence scores. Assign the box's class label as the class with the highest score.
classIds = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
classId = np.argmax(scores)
confidence = scores[classId]
if confidence > confThreshold:
print(scores)
center_x = int(detection[0] * frameWidth)
center_y = int(detection[1] * frameHeight)
width = int(detection[2] * frameWidth)
height = int(detection[3] * frameHeight)
left = int(center_x - width / 2)
top = int(center_y - height / 2)
classIds.append(classId)
confidences.append(float(confidence))
boxes.append([left, top, width, height])
# Perform non maximum suppression to eliminate redundant overlapping boxes with
# lower confidences.
indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
i = i[0]
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
drawPred(classIds[i], confidences[i], left, top, left + width, top + height)
# Process inputs
winName = 'Deep learning object detection in OpenCV'
cv.namedWindow(winName, cv.WINDOW_NORMAL)
outputFile = "yolo_out_py.avi"
if (args.image):
# Open the image file
if not os.path.isfile(args.image):
print("Input image file ", args.image, " doesn't exist")
sys.exit(1)
cap = cv.VideoCapture(args.image)
outputFile = args.image[:-4]+'_yolo_out_py.jpg'
elif (args.video):
if not os.path.isfile(args.video):
print("Input video file ", args.video, " doesn't exist")
sys.exit(1)
cap = cv.VideoCapture(args.video)
outputFile = args.video[:-4]+'_yolo_out_py.avi'
else:
cap = cv.VideoCapture(0)
if (not args.image):
vid_writer = cv.VideoWriter(outputFile, cv.VideoWriter_fourcc('M','J','P','G'), 5, (
round(cap.get(cv.CAP_PROP_FRAME_WIDTH)),round(cap.get(cv.CAP_PROP_FRAME_HEIGHT))))
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
if not hasFrame:
print("Done processing !!!")
print("Output file is stored as ", outputFile)
cv.waitKey(3000)
# Release device
cap.release()
break
# Create a 4D blob from a frame.
blob = cv.dnn.blobFromImage(frame, 1/255, (inpWidth, inpHeight), [0,0,0], 1, crop=False)
# Sets the input to the network
net.setInput(blob)
# Runs the forward pass to get output of the output layers
outs = net.forward(getOutputsNames(net))
# Remove the bounding boxes with low confidence
postprocess(frame, outs)
# Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for
each of the layers(in layersTimes)
t, _ = net.getPerfProfile()
label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
if (args.image):
cv.imwrite(outputFile, frame.astype(np.uint8))
else:
vid_writer.write(frame.astype(np.uint8))
cv.imshow(winName, frame)
这可能是因为独立的逻辑分类器。此描述可能有助于您理解。
类预测：YOLOv3为每个类使用独立的逻辑分类器，而不是常规的softmax层。这样做是为了使分类成为多标签分类。它意味着什么以及如何增加价值？举个例子，照片中显示的是一个女性，模型是在人和女性身上训练的，这里有一个softmax将导致类别概率在这两个类别之间划分，比如说0.4和0.45的概率。但独立分类器解决了这个问题，并为每个类别给出了是与否的概率，比如照片中有一个女人的概率是0.8，照片中有个人的概率是0.9，我们可以将对象标记为人和女人。
https://github.com/AvivSham/YOLO_V3_from_scratch_colab
同样的问题！我终于找到了解决办法。
这只是因为OpenCV在这里实现了一个硬编码阈值：https://github.com/opencv/opencv/blob/4.5.3/modules/dnn/src/layers/region_layer.cpp#L83
您需要在每个yolo层的cfg文件中覆盖它(3次(，如：thresh=0.0001
该阈值在YoloV2中相当低，但在Yolov3->在这个阈值下的每一次检测都将等于零(https://github.com/opencv/opencv/blob/4.5.3/modules/dnn/src/layers/region_layer.cpp#L316)
PS：这个阈值与darknet_version 中的nms_thresh和hier_thresh有点不明确