diff --git a/src/Yolov4_Vehicle_inspection/kmeans_for_anchors.py b/src/Yolov4_Vehicle_inspection/kmeans_for_anchors.py new file mode 100644 index 0000000000..cc75413407 --- /dev/null +++ b/src/Yolov4_Vehicle_inspection/kmeans_for_anchors.py @@ -0,0 +1,113 @@ +#-------------------------------------------------------------------------------------------------# +# kmeans虽然会对数据集中的框进行聚类,但是很多数据集由于框的大小相近,聚类出来的9个框相差不大, +# 这样的框反而不利于模型的训练。因为不同的特征层适合不同大小的先验框,越浅的特征层适合越大的先验框 +# 原始网络的先验框已经按大中小比例分配好了,不进行聚类也会有非常好的效果。 +#-------------------------------------------------------------------------------------------------# +import glob +import xml.etree.ElementTree as ET + +import numpy as np + +def cas_iou(box,cluster): + x = np.minimum(cluster[:,0],box[0]) + y = np.minimum(cluster[:,1],box[1]) + + intersection = x * y + area1 = box[0] * box[1] + + area2 = cluster[:,0] * cluster[:,1] + iou = intersection / (area1 + area2 -intersection) + + return iou + +def avg_iou(box,cluster): + return np.mean([np.max(cas_iou(box[i],cluster)) for i in range(box.shape[0])]) + +def kmeans(box,k): + # 取出一共有多少框 + row = box.shape[0] + + # 每个框各个点的位置 + distance = np.empty((row,k)) + + # 最后的聚类位置 + last_clu = np.zeros((row,)) + + np.random.seed() + + # 随机选5个当聚类中心 + cluster = box[np.random.choice(row,k,replace = False)] + # cluster = random.sample(row, k) + while True: + # 计算每一行距离五个点的iou情况。 + for i in range(row): + distance[i] = 1 - cas_iou(box[i],cluster) + + # 取出最小点 + near = np.argmin(distance,axis=1) + + if (last_clu == near).all(): + break + + # 求每一个类的中位点 + for j in range(k): + cluster[j] = np.median( + box[near == j],axis=0) + + last_clu = near + + return cluster + +def load_data(path): + data = [] + # 对于每一个xml都寻找box + for xml_file in glob.glob('{}/*xml'.format(path)): + tree = ET.parse(xml_file) + height = int(tree.findtext('./size/height')) + width = int(tree.findtext('./size/width')) + if height<=0 or width<=0: + continue + + # 对于每一个目标都获得它的宽高 + for obj in tree.iter('object'): + xmin = int(float(obj.findtext('bndbox/xmin'))) / width + ymin = int(float(obj.findtext('bndbox/ymin'))) / height + xmax = int(float(obj.findtext('bndbox/xmax'))) / width + ymax = int(float(obj.findtext('bndbox/ymax'))) / height + + xmin = np.float64(xmin) + ymin = np.float64(ymin) + xmax = np.float64(xmax) + ymax = np.float64(ymax) + # 得到宽高 + data.append([xmax-xmin,ymax-ymin]) + return np.array(data) + + +if __name__ == '__main__': + # 运行该程序会计算'./VOCdevkit/VOC2007/Annotations'的xml + # 会生成yolo_anchors.txt + SIZE = 416 + anchors_num = 9 + # 载入数据集,可以使用VOC的xml + path = r'./VOCdevkit/VOC2007/Annotations' + + # 载入所有的xml + # 存储格式为转化为比例后的width,height + data = load_data(path) + + # 使用k聚类算法 + out = kmeans(data,anchors_num) + out = out[np.argsort(out[:,0])] + print('acc:{:.2f}%'.format(avg_iou(data,out) * 100)) + print(out*SIZE) + data = out*SIZE + f = open("yolo_anchors.txt", 'w') + row = np.shape(data)[0] + for i in range(row): + if i == 0: + x_y = "%d,%d" % (data[i][0], data[i][1]) + else: + x_y = ", %d,%d" % (data[i][0], data[i][1]) + f.write(x_y) + f.close() diff --git a/src/Yolov4_Vehicle_inspection/move_pic.py b/src/Yolov4_Vehicle_inspection/move_pic.py new file mode 100644 index 0000000000..5b4903e7e5 --- /dev/null +++ b/src/Yolov4_Vehicle_inspection/move_pic.py @@ -0,0 +1,31 @@ +import os +import random +import shutil + +# xml路径的地址 +XmlPath = r'xml_train' +# 原图片的地址 +pictureBasePath = r"E:\Insight-MVT_Annotation_Train" +# 保存图片的地址 +saveBasePath = r"E:\picture_train" + +total_xml = os.listdir(XmlPath) +num = len(total_xml) +list = range(num) +if os.path.exists(saveBasePath) == False: # 判断文件夹是否存在 + os.makedirs(saveBasePath) +from tqdm import tqdm +for xml in tqdm(total_xml): + xml_temp = xml.split("__") + folder = xml_temp[0] + filename = xml_temp[1].split(".")[0] + ".jpg" + # print(folder) + # print(filename) + temp_pictureBasePath = os.path.join(pictureBasePath, folder) + filePath = os.path.join(temp_pictureBasePath, filename) + # print(filePath) + newfile = xml.split(".")[0] + ".jpg" + newfile_path = os.path.join(saveBasePath, newfile) + # print(newfile_path) + shutil.copyfile(filePath, newfile_path) +print("xml file total number", num) \ No newline at end of file diff --git a/src/Yolov4_Vehicle_inspection/test.py b/src/Yolov4_Vehicle_inspection/test.py new file mode 100644 index 0000000000..d486e2c0c1 --- /dev/null +++ b/src/Yolov4_Vehicle_inspection/test.py @@ -0,0 +1,15 @@ +#--------------------------------------------# +# 该部分代码只用于看网络结构,并非测试代码 +# map测试请看get_dr_txt.py、get_gt_txt.py +# 和get_map.py +#--------------------------------------------# +import torch +from torchsummary import summary + +from nets.yolo4 import YoloBody + +if __name__ == "__main__": + # 需要使用device来指定网络在GPU还是CPU运行 + device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') + model = YoloBody(3,20).to(device) + summary(model, input_size=(3, 416, 416))