官方地址:https://github.com/ultralytics/yolov5
官方链接:https://github.com/ultralytics/yolov5/releases
yolov5l.pt
yolov5s.pt
yolov5x.pt
yolov5m.pt
将权重文件放入yolov5-master/weights
文件夹下
pip3 install -r requirements.txt
git clone https://github.com/ultralytics/yolov5/releases
cd yolov5-master
#1 利用自带摄像头检测
python3 detec.py --source 0
#2 else
python detect.py --source 0 # webcam
file.jpg # image
file.mp4 # video
# 3 批量检测输出
python3 detect.py --source data/images --weights yolov5s.pt --conf 0.25
在yolov5-master
文件夹构建my_Data
文件夹存放自己数据
数据集结构显示:
myData
......images #存放图像
......Annotations #存放图像对应的xml文件
......ImageSets/Main #存放训练/存放train.txt/val.txt/test.txt/trainval.txt文件
......test.py #生成train.txt/val.txt/test.txt/trainval.txt文件
建立my_test.py文件:
# coding:utf-8
import os
import random
import argparse
parser = argparse.ArgumentParser()
#xml文件的地址,根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#数据集的划分,地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 1.0
train_percent = 0.9
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
os.makedirs(txtsavepath)
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
for i in list_index:
name = total_xml[i][:-4] + '\n'
if i in trainval:
file_trainval.write(name)
if i in train:
file_train.write(name)
else:
file_val.write(name)
else:
file_test.write(name)
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()
创建my_label.py文件
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["person"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
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
def convert_annotation(image_id):
in_file = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for image_set in sets:
if not os.path.exists('/home/wyh/keti/mubiao/yolov5-master/my_Data/labels/'):
os.makedirs('/home/wyh/keti/mubiao/yolov5-master/my_Data/labels/')
image_ids = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write(abs_path + '/home/wyh/keti/mubiao/yolov5-master/my_Data/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
运行后在my_Data文件夹下生成labels文件夹和三个txt文件,labels中为不同图像的标注文件,
labels文件格式
0 0.8095238095238095 0.53 0.3630952380952381 0.892
0 0.25297619047619047 0.604 0.41666666666666663 0.46
0 0.30952380952380953 0.301 0.4583333333333333 0.28200000000000003
文件内容:
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
# Train command: python train.py --data voc.yaml
# Default dataset location is next to /yolov5:
# /parent_folder
# /VOC
# /yolov5
# download command/URL (optional)
download: bash data/scripts/get_coco.sh
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: /home/wyh/keti/mubiao/yolov5-master/my_Data/images # 16551 images
val: /home/wyh/keti/mubiao/yolov5-master/my_Data/images # 4952 images
#test: /home/wyh/keti/mubiao/yolov5-master/my_Data/test.txt
# number of classes
nc: 1
# class names
names: [ 'person' ]
注:将labels文件夹和images文件夹修改成如下格式
images
......train #原始图片
......val
labels
......train #label文件
......val
# parameters
nc: 1 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
......
修改nc 、根据情况修改anchors
import numpy as np
def iou(box, clusters):
"""
Calculates the Intersection over Union (IoU) between a box and k clusters.
:param box: tuple or array, shifted to the origin (i. e. width and height)
:param clusters: numpy array of shape (k, 2) where k is the number of clusters
:return: numpy array of shape (k, 0) where k is the number of clusters
"""
x = np.minimum(clusters[:, 0], box[0])
y = np.minimum(clusters[:, 1], box[1])
if np.count_nonzero(x == 0) > 0 or np.count_nonzero(y == 0) > 0:
raise ValueError("Box has no area")
intersection = x * y
box_area = box[0] * box[1]
cluster_area = clusters[:, 0] * clusters[:, 1]
iou_ = intersection / (box_area + cluster_area - intersection)
return iou_
def avg_iou(boxes, clusters):
"""
Calculates the average Intersection over Union (IoU) between a numpy array of boxes and k clusters.
:param boxes: numpy array of shape (r, 2), where r is the number of rows
:param clusters: numpy array of shape (k, 2) where k is the number of clusters
:return: average IoU as a single float
"""
return np.mean([np.max(iou(boxes[i], clusters)) for i in range(boxes.shape[0])])
def translate_boxes(boxes):
"""
Translates all the boxes to the origin.
:param boxes: numpy array of shape (r, 4)
:return: numpy array of shape (r, 2)
"""
new_boxes = boxes.copy()
for row in range(new_boxes.shape[0]):
new_boxes[row][2] = np.abs(new_boxes[row][2] - new_boxes[row][0])
new_boxes[row][3] = np.abs(new_boxes[row][3] - new_boxes[row][1])
return np.delete(new_boxes, [0, 1], axis=1)
def kmeans(boxes, k, dist=np.median):
"""
Calculates k-means clustering with the Intersection over Union (IoU) metric.
:param boxes: numpy array of shape (r, 2), where r is the number of rows
:param k: number of clusters
:param dist: distance function
:return: numpy array of shape (k, 2)
"""
rows = boxes.shape[0]
distances = np.empty((rows, k))
last_clusters = np.zeros((rows,))
np.random.seed()
# the Forgy method will fail if the whole array contains the same rows
clusters = boxes[np.random.choice(rows, k, replace=False)]
while True:
for row in range(rows):
distances[row] = 1 - iou(boxes[row], clusters)
nearest_clusters = np.argmin(distances, axis=1)
if (last_clusters == nearest_clusters).all():
break
for cluster in range(k):
clusters[cluster] = dist(boxes[nearest_clusters == cluster], axis=0)
last_clusters = nearest_clusters
return clusters
if __name__ == '__main__':
a = np.array([[1, 2, 3, 4], [5, 7, 6, 8]])
print(translate_boxes(a))
聚类生成新anchors的文件new_anchors.py
# -*- coding: utf-8 -*-
# 根据标签文件求先验框
import os
import numpy as np
import xml.etree.cElementTree as et
from kmeans import kmeans, avg_iou
FILE_ROOT = "/home/wyh/keti/mubiao/yolov5-master/my_Data/" # 根路径
ANNOTATION_ROOT = "Annotations" # 数据集标签文件夹路径
ANNOTATION_PATH = FILE_ROOT + ANNOTATION_ROOT
ANCHORS_TXT_PATH = "/home/wyh/keti/mubiao/yolov5-master/my_Data/anchors.txt"
CLUSTERS = 1
CLASS_NAMES = ['person']
def load_data(anno_dir, class_names):
xml_names = os.listdir(anno_dir)
boxes = []
for xml_name in xml_names:
xml_pth = os.path.join(anno_dir, xml_name)
tree = et.parse(xml_pth)
width = float(tree.findtext("./size/width"))
height = float(tree.findtext("./size/height"))
for obj in tree.findall("./object"):
cls_name = obj.findtext("name")
if cls_name in class_names:
xmin = float(obj.findtext("bndbox/xmin")) / width
ymin = float(obj.findtext("bndbox/ymin")) / height
xmax = float(obj.findtext("bndbox/xmax")) / width
ymax = float(obj.findtext("bndbox/ymax")) / height
box = [xmax - xmin, ymax - ymin]
boxes.append(box)
else:
continue
return np.array(boxes)
if __name__ == '__main__':
anchors_txt = open(ANCHORS_TXT_PATH, "w")
train_boxes = load_data(ANNOTATION_PATH, CLASS_NAMES)
count = 1
best_accuracy = 0
best_anchors = []
best_ratios = []
for i in range(10): ##### 可以修改,不要太大,否则时间很长
anchors_tmp = []
clusters = kmeans(train_boxes, k=CLUSTERS)
idx = clusters[:, 0].argsort()
clusters = clusters[idx]
# print(clusters)
for j in range(CLUSTERS):
anchor = [round(clusters[j][0] * 640, 2), round(clusters[j][1] * 640, 2)]
anchors_tmp.append(anchor)
print(f"Anchors:{anchor}")
temp_accuracy = avg_iou(train_boxes, clusters) * 100
print("Train_Accuracy:{:.2f}%".format(temp_accuracy))
ratios = np.around(clusters[:, 0] / clusters[:, 1], decimals=2).tolist()
ratios.sort()
print("Ratios:{}".format(ratios))
print(20 * "*" + " {} ".format(count) + 20 * "*")
count += 1
if temp_accuracy > best_accuracy:
best_accuracy = temp_accuracy
best_anchors = anchors_tmp
best_ratios = ratios
anchors_txt.write("Best Accuracy = " + str(round(best_accuracy, 2)) + '%' + "\r\n")
anchors_txt.write("Best Anchors = " + str(best_anchors) + "\r\n")
anchors_txt.write("Best Ratios = " + str(best_ratios))
anchors_txt.close()
进行路径修改
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='my_Data/my_yolov5s.yaml', help='model.yaml path')
parser.add_argument('--data', type=str, default='my_Data/my_data.yaml', help='data.yaml path')
parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=300)
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
参数修改cfg\data等
epochs:指的就是训练过程中整个数据集将被迭代多少次,显卡不行你就调小点。
batch-size:一次看完多少张图片才进行权重更新,梯度下降的mini-batch,显卡不行你就调小点。
cfg:存储模型结构的配置文件
data:存储训练、测试数据的文件
img-size:输入图片宽高,显卡不行你就调小点。
rect:进行矩形训练
resume:恢复最近保存的模型开始训练
nosave:仅保存最终checkpoint
notest:仅测试最后的epoch
evolve:进化超参数
bucket:gsutil bucket
cache-images:缓存图像以加快训练速度
weights:权重文件路径
name: 重命名results.txt to results_name.txt
device:cuda device, i.e. 0 or 0,1,2,3 or cpu
adam:使用adam优化
multi-scale:多尺度训练,img-size +/- 50%
single-cls:单类别的训练集
训练:
python3 train.py --img 640 --batch 8 --epoch 5 --data my_Data/my_data.yaml --cfg my_Data/my_yolov5s.yaml --weights weights/yolov5s.pt --device cpu # 0号GPU -device 0
训练后生成runs文件夹
tensorboard --logdir=runs
参考链接:https://blog.csdn.net/qq_36756866/article/details/109111065