目标检测-opencv-yolov3，包含训练以及测试代码

以你之姓@ 2023-02-13 03:22 3阅读 0赞

### splitTrainTest ###

# -*- coding: utf-8 -*-
    """
    Created on 2020/5/26 22:21
    @author: Johnson
    Email:593956670@qq.com
    """
    import random
    import os 
    import subprocess
    import sys
    
    def split_data_set(image_dir):
        f_val = open("test.txt","w")
        f_train = open("train.txt","w")
        path,dirs,files = next(os.walk(image_dir))
        data_size = len(files)
        ind = 0
        data_test_size = int(0.1*data_size)
        test_array = random.sample(range(data_size),k=data_test_size)
        
        for f in os.listdir(image_dir):
            if (f.split(".")[1]=="jpg"):
                ind+=1
                if ind in test_array:
                    f_val.write(image_dir+"/"+f+"\n")
                else:
                    f_train.write(image_dir+"/"+f+"\n")
    split_data_set(sys.argv[1])

### plotTrainloss ###

# -*- coding: utf-8 -*-
    """
    Created on 2020/5/26 22:28
    @author: Johnson
    Email:593956670@qq.com
    """
    import sys
    import matplotlib.pyplot as plt
    
    lines = []
    for line in open(sys.argv[1]):
        if "avg" in line:
            lines.append(line)
    
    iterations = []
    avg_loss = []
    
    print('Retrieving data and plotting training loss graph...')
    for i in range(len(lines)):
        lineParts = lines[i].split(',')
        iterations.append(int(lineParts[0].split(':')[0]))
        avg_loss.append(float(lineParts[1].split()[0]))
    
    fig = plt.figure()
    for i in range(0, len(lines)):
        plt.plot(iterations[i:i+2], avg_loss[i:i+2], 'r.-')
    
    plt.xlabel('Batch Number')
    plt.ylabel('Avg Loss')
    fig.savefig('training_loss_plot.png', dpi=1000)
    
    print('Done! Plot saved as training_loss_plot.png')

### darknet-yolov3.cfg ###

# Based on cfg/yolov3-voc.cfg
    
    [net]
    # Testing
    # batch=1
    # subdivisions=1
    # Training
    batch=64
    subdivisions=16
    width=416
    height=416
    channels=3
    momentum=0.9
    decay=0.0005
    angle=0
    saturation = 1.5
    exposure = 1.5
    hue=.1
    
    learning_rate=0.001
    burn_in=400
    max_batches=5200
    policy=steps
    steps=3800
    scales=.1
    
    [convolutional]
    batch_normalize=1
    filters=32
    size=3
    stride=1
    pad=1
    activation=leaky
    
    # Downsample
    
    [convolutional]
    batch_normalize=1
    filters=64
    size=3
    stride=2
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=32
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=64
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    # Downsample
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=3
    stride=2
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=64
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=64
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    # Downsample
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=2
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    # Downsample
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=2
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    # Downsample
    
    [convolutional]
    batch_normalize=1
    filters=1024
    size=3
    stride=2
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=1024
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=1024
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=1024
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=1024
    size=3
    stride=1
    pad=1
    activation=leaky
    
    [shortcut]
    from=-3
    activation=linear
    
    ######################
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=1024
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=1024
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=512
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=1024
    activation=leaky
    
    [convolutional]
    size=1
    stride=1
    pad=1
    # filters = (num/3) * (5+classes)
    filters=18
    activation=linear
    
    [yolo]
    mask = 6,7,8
    anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
    classes=1
    num=9
    jitter=.3
    ignore_thresh = .5
    truth_thresh = 1
    random=1
    
    [route]
    layers = -4
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [upsample]
    stride=2
    
    [route]
    layers = -1, 61
    
    
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=512
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=512
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=256
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=512
    activation=leaky
    
    [convolutional]
    size=1
    stride=1
    pad=1
    # filters = (num/3) * (5+classes)
    filters=18
    activation=linear
    
    [yolo]
    mask = 3,4,5
    anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
    classes=1
    num=9
    jitter=.3
    ignore_thresh = .5
    truth_thresh = 1
    random=1
    
    [route]
    layers = -4
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [upsample]
    stride=4
    
    [route]
    layers = -1, 11
    
    
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=256
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=256
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    filters=128
    size=1
    stride=1
    pad=1
    activation=leaky
    
    [convolutional]
    batch_normalize=1
    size=3
    stride=1
    pad=1
    filters=256
    activation=leaky
    
    [convolutional]
    size=1
    stride=1
    pad=1
    # filters = (num/3) * (5+classes)
    filters=18
    activation=linear
    
    [yolo]
    mask = 0,1,2
    anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
    classes=1
    num=9
    jitter=.3
    ignore_thresh = .5
    truth_thresh = 1
    random=1

### darknet.data ###

classes = 1
    train  = /data-ssd/sunita/snowman/snowman_train.txt
    valid  = /data-ssd/sunita/snowman/snowman_test.txt
    names = /data-ssd/sunita/snowman/classes.names
    backup = /data-ssd/sunita/snowman/weights/

### classes.names ###

snowman

### object\_detection\_yolo.py ###

# -*- coding: utf-8 -*-
    """
    Created on 2020/5/26 22:29
    @author: Johnson
    Email:593956670@qq.com
    """
    # Usage example:  python3 object_detection_yolo.py --video=run.mp4
    #                 python3 object_detection_yolo.py --image=bird.jpg
    import cv2 as cv
    import argparse
    import sys
    import numpy as np
    import os.path
    
    #初始化参数
    confThreshold = 0.5 #置信度阈值
    nmsThreshold = 0.4 # nms阈值
    
    inpWidth = 416 #608
    inpHight = 416 #608
    
    parser = argparse.ArgumentParser()
    parser.add_argument("--image",help="Path to image file")
    parser.add_argument("--video",help="Path to video file")
    
    #分类名称
    classesFile = "classes.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 = "darknet-yolov3.cfg";
    modelWeights = "darknet-yolov3_final.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):
        # Get the names of all the layers in the network
        layersNames = net.getLayerNames()
        # Get the names of the output layers, i.e. the layers with unconnected outputs
        return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]
    
    #darw the predicted bounding box
    def drawPred(classId,conf,letf,top,right,bottom):
        #draw the bounding box
        # cv.rectangle(frame,(left,top),(right,bottom),(255,178,50),3)
        cv.rectangle(frame, (left, top), (right, bottom), (0, 255, 0), 3)
        label = "%.2f"%conf
        #get the label for the class name and its confidence
        if classes:
            assert (classId<len(classes))
        # 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(1.5 * labelSize[1])), (left + round(1.5 * labelSize[0]), top + baseLine),
                     (0, 0, 255), cv.FILLED)
        # cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine),    (255, 255, 255), cv.FILLED)
        cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 0), 2)
    
    # Remove the bounding boxes with low confidence using non-maxima suppression
    def postprocess(frame, outs):
        frameHeight = frame.shape[0]
        frameWidth = frame.shape[1]
    
        classIds = []
        confidences = []
        boxes = []
        # 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:
            print("out.shape : ", out.shape)
            for detection in out:
                #if detection[4]>0.001:
                scores = detection[5:]
                classId = np.argmax(scores)
                #if scores[classId]>confThreshold:
                confidence = scores[classId]
                if detection[4]>confThreshold:
                    print(detection[4], " - ", scores[classId], " - th : ", confThreshold)
                    print(detection)
                if confidence > confThreshold:
                    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):
        # Open the video file
        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:
        # Webcam input
        cap = cv.VideoCapture(0)
    
    # Get the video writer initialized to save the output video
    if (not args.image):
        vid_writer = cv.VideoWriter(outputFile, cv.VideoWriter_fourcc('M', 'J', 'P', 'G'), 30,
                                    (round(cap.get(cv.CAP_PROP_FRAME_WIDTH)), round(cap.get(cv.CAP_PROP_FRAME_HEIGHT))))
    
    while cv.waitKey(1) < 0:
    
        # get frame from the video
        hasFrame, frame = cap.read()
    
        # Stop the program if reached end of video
        if not hasFrame:
            print("Done processing !!!")
            print("Output file is stored as ", outputFile)
            cv.waitKey(3000)
            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))
    
        # Write the frame with the detection boxes
        if (args.image):
            cv.imwrite(outputFile, frame.astype(np.uint8));
        else:
            vid_writer.write(frame.astype(np.uint8))
    
        cv.imshow(winName, frame)