Pytorch 版YOLOV5训练自己的数据集

我们曾经梦寐以求的权利，白嫖的权利：

1、环境搭建

https://github.com/ultralytics/yolov5

2、安装需要的软件

 pip install -U -r requirements.txt

3、准备数据

在data文件下建立上面三个文件（Annotations、images与ImageSets，labels后续我们脚本生成）其中Annotations存放xml文件，images图像，ImageSets新建Main文件存放train与test文件（脚本生成），labels是标签文件

划分训练集与测试集（为了充分利用数据集我们只划分这两个），生成的在ImageSets / Main文件下

import os
import random

trainval_percent = 0.2   #可自行进行调节
train_percent = 1
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

#ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
#fval = open('ImageSets/Main/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        #ftrainval.write(name)
        if i in train:
            ftest.write(name)
        #else:
            #fval.write(name)
    else:
        ftrain.write(name)

#ftrainval.close()
ftrain.close()
#fval.close()
ftest.close()

建立voc_labels文件生成labels标签文件

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
sets = ['train', 'test']
 
classes = ['apple','orange']  #自己训练的类别
 
 
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)
 
 
def convert_annotation(image_id):
    in_file = open('data/Annotations/%s.xml' % (image_id))
    out_file = open('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))
        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('data/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

4、配置训练文件

在data目录下新建fruit.yaml，配置训练的数据

# COCO 2017 dataset http://cocodataset.org
# Download command: bash yolov5/data/get_coco2017.sh
# Train command: python train.py --data ./data/coco.yaml
# Dataset should be placed next to yolov5 folder:
#   /parent_folder
#     /coco
#     /yolov5


# train and val datasets (image directory or *.txt file with image paths)
train: xx/xx/train2017.txt  # 上面我们生成的train，根据自己的路径进行更改
val: xx/xx/val2017.txt  # 上面我们生成的test
#test: ../coco/test-dev2017.txt  # 20k images for submission to https://competitions.codalab.org/competitions/20794

# number of classes
nc: 2   #训练的类别
 
# class names
names: ['apple','orange']

# Print classes
# with open('data/coco.yaml') as f:
#   d = yaml.load(f, Loader=yaml.FullLoader)  # dict
#   for i, x in enumerate(d['names']):
#     print(i, x)

models文件（采用那个yaml我们更改那个），例如采用yolov5s.yaml：

# parameters
nc: 2  # number of classes 训练的类别数
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

# yolov5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 1-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
   [-1, 3, Bottleneck, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
   [-1, 9, Bottleneck, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
   [-1, 9, Bottleneck, [512]],
   [-1, 1, Conv, [1024, 3, 2]], # 8-P5/32
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, Bottleneck, [1024]],  # 10
  ]

# yolov5 head
head:
  [[-1, 3, Bottleneck, [1024, False]],  # 11
   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 12 (P5/32-large)

   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 1, Conv, [512, 1, 1]],
   [-1, 3, Bottleneck, [512, False]],
   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 17 (P4/16-medium)

   [-2, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 3, Bottleneck, [256, False]],
   [-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1, 0]],  # 22 (P3/8-small)

   [[], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

5、训练

python train.py --data data/fruit.yaml --cfg models/yolov5s.yaml --weights '' --batch-size 16 --epochs 100

这里想加载预训练权重要更改下代码，不然会报错：

train.py中115行（日期2020.6.9）

        try:
            #ckpt['model'] = \
                #{k: v for k, v in ckpt['model'].state_dict().items() if model.state_dict()[k].numel() == v.numel()}
            ckpt['model'] = \
                {k: v for k, v in ckpt['model'].state_dict().items() if k in model.state_dict().keys()\
                 and model.state_dict()[k].numel() == v.numel()

训练命令：

python train.py --data data/fruit.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --batch-size 16 --epochs 100

6、测试：

 python detect.py --source file.jpg  # image 
                            file.mp4  # video
                            ./dir  # directory
                            0  # webcam
                            rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                            http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream

 

官方指南，你值得拥有：https://github.com/ultralytics/yolov5