GitHub链接：https://github.com/ultralytics/yolov3
参考链接：https://blog.csdn.net/qq_44787464/article/details/99736670
1.requirements
pip install -r requirements.txt
Python>=3.7
PyTorch>=1.5
Cython
numpy==1.17
opencv-python
torch>=1.5
matplotlib
pillow
tensorboard
PyYAML>=5.3
torchvision
scipy
tqdm
git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI
2.数据准备（省略标记）
准备自己的数据集（voc）
├── Annotations 进行 detection 任务时的标签文件，xml 形式，文件名与图片名一一对应
├── ImageSets 包含三个子文件夹 Layout（不使用）、Main、Segmentation（不使用），其中 Main 存放的是分类和检测的数据集分割文件
├── JPEGImages 存放 .jpg 格式的图片文件
├── SegmentationClass 存放按照 class 分割的图片（不使用）
└── SegmentationObject 存放按照 object 分割的图片（不使用）
├── Main
│ ├── train.txt 写着用于训练的图片名称
│ ├── val.txt 写着用于验证的图片名称
│ ├── trainval.txt train与val的合集
│ ├── test.txt 写着用于测试的图片名称
数据Annotations和JPEGImages放入data目录下，并新建文件ImageSets，labels，复制JPEGImages，重命名images
（1）生成train.txt,val.txt,test.txt（无路径）即：
getText.py程序
import os
import random
trainval_percent = 0.1#数据少就1：9
train_percent = 0.9
xmlfilepath = '/data/Annotations'
txtsavepath = '/data/ImageSets'
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('/data/ImageSets/trainval.txt', 'w')
ftest = open('/data/ImageSets/test.txt', 'w')
ftrain = open('/data/ImageSets/train.txt', 'w')
fval = open('/data/ImageSets/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()
(2)生成标签信息以及带路径的train.txt,val.txt等文件
voc_label.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test', 'val']
classes = ["1","2","3","4","5","6"] # 修改类别
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()
print(wd)
for image_set in sets:
if not os.path.exists('data/labels/'):
os.makedirs('data/labels/')
image_ids = open('data/ImageSets/%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()
产生下面的文件：
（3）配置生成yaml文件，复制data文件夹下coco.yaml生成自己的dataset.yaml
# COCO 2017 dataset http://cocodataset.org
# Train command: python train.py --data coco.yaml
# Default dataset location is next to /yolov3:
# /parent_folder
# /coco
# /yolov3
# download command/URL (optional)
download: bash data/scripts/get_coco.sh #没用注释掉
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: ../coco/train2017.txt #（修改为带文件路径的train.txt）
val: ../coco/val2017.txt # (同上)
test: ../coco/test-dev2017.txt #(同上)
# number of classes
nc: 80
# class names（修改为自己的类别）
names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
'hair drier', 'toothbrush' ]
# 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)
3.训练（yolov3 训练1600张图片，使用泰坦，batchsize=24，epoch=300，训练3h）
训练之前主要修改配置文件yolov3.yaml文件，不修改网络结构的话，只修改nc的值就可以。
准备weights文件下的权重https://github.com/ultralytics/yolov3/releases
# parameters
nc: 80 # number of classes(从1开始数)（修改）
depth_multiple: 1.0 # model depth multiple（控制模型的深度）
width_multiple: 1.0 # layer channel multiple（控制卷积核的个数）
# 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
# darknet53 backbone
backbone:
# [from, number, module, args]
# form：-1 代表是从上一层获得的输入，-2表示从上两层获得的输入（head同理）
# number列参数：1表示只有一个，3表示有三个相同的模块。
[[-1, 1, Conv, [32, 3, 1]], # 0
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
[-1, 1, Bottleneck, [64]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 2, Bottleneck, [128]],
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
[-1, 8, Bottleneck, [256]],
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
[-1, 8, Bottleneck, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
[-1, 4, Bottleneck, [1024]], # 10
]
# YOLOv3 head
head:
[[-1, 1, Bottleneck, [1024, False]],
[-1, 1, Conv, [512, [1, 1]]],
[-1, 1, Conv, [1024, 3, 1]],
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 8], 1, Concat, [1]], # cat backbone P4
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P3
[-1, 1, Bottleneck, [256, False]],
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
修改train.py文件’–weights’，’–cfg’，’–data’，’–epochs’（默认300）
，’–batch-size’，’–device’
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='weights/best.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='models/yolov3.yaml', help='model.yaml path')
parser.add_argument('--data', type=str, default='data/dataset.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=100)
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')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--notest', action='store_true', help='only test final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
parser.add_argument('--project', default='runs/train', help='save to project/name')
parser.add_argument('--entity', default=None, help='W&B entity')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
opt = parser.parse_args()
开始训练
python train.py --data /tmp/pycharm_project_38/data/dataset.yaml --cfg /tmp/pycharm_project_38/models/yolov3.yaml --weights 'weights/yolov3.pt' --batch-size 24
运行后自动产生output结果文件
4检测
python3 .\detect.py --names ./data/cell/rbc.names --cfg ./cfg/yolov3-tiny.cfg --weights ./weights/best.pt
python detect.py
版权声明：本文为CSDN博主「被窝里的奶油卷」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_41769570/article/details/116723675
暂无评论