使用mmyolo检测工具箱，完成yolo系列算法的训练，包括环境的搭建及yolo系列算法的配置文件等。
mmyolo官方地址：https://github.com/open-mmlab/mmdeploy
相关文档： https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/docs/zh_cn/get_started.md
一、环境搭建
1.创建虚拟环境
conda create --name mmyolo python=3.8 -y
激活虚拟环境：
conda activate mmyolo
2.安装pytorch、torchvision
根据自己的配置安装相应版本
pip install torch==1.7.1+cu101 torchvision==0.8.2+cu101 -f https://download.pytorch.org/whl/torch_stable.html
或手动下载，地址：https://download.pytorch.org/whl/torch_stable.html
3.下载I MMEngine 、 MMCV和MMDET3.x
pip install -U openmim mim install mmengine mim install 'mmcv>=2.0.0rc1' mim install "mmdet>=3.0.0rc5,<3.1.0" 4.下载mmyolo并编译 git clone https://github.com/open-mmlab/mmyolo.git cd mmyolo # Install albumentations pip install -r requirements/albu.txt # Install MMYOLO mim install -v -e .
二、训练yolo系列算法（以yolo6和yolox为例）
yolo5~yolo8训练的config大致相同，yolox略有不同
1.构造数据集
使用coco格式数据集进行训练，使用labelme标注，然后使用如下代码进行转换：
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./tran.json'):
'''
:param labelme_json: 所有labelme的json文件路径组成的列表
:param save_json_path: json保存位置
'''
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
# self.data_coco = {}
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
self.images.append(self.image(data, num))
for shapes in data['shapes']:
label = shapes['label']
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points']#这里的point是用rectangle标注得到的，只有两个点，需要转成四个点
#points.append([points[0][0],points[1][1]])
#points.append([points[1][0],points[0][1]])
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data['imageData']) # 解析原图片数据
# img=io.imread(data['imagePath']) # 通过图片路径打开图片
# img = cv2.imread(data['imagePath'], 0)
height, width = img.shape[:2]
img = None
image['height'] = height
image['width'] = width
image['id'] = num + 1
#image['file_name'] = data['imagePath'].split('/')[-1]
image['file_name'] = data['imagePath'][3:14]
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = 'Cancer'
categorie['id'] = len(self.label) + 1 # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
annotation['segmentation'] = [list(np.asarray(points).flatten())]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
# annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
# list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
# annotation['category_id'] = self.getcatid(label)
annotation['category_id'] = self.getcatid(label)#注意，源代码默认为1
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label == categorie['name']:
return categorie['id']
return 1
def getbbox(self, points):
# img = np.zeros([self.height,self.width],np.uint8)
# cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线
# cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
'''从mask反算出其边框
mask：[h,w] 0、1组成的图片
1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
'''
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
# 解析右下角行列号
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
return [left_top_c, left_top_r, right_bottom_c - left_top_c,
right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式
def polygons_to_mask(self, img_shape, polygons):
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco['images'] = self.images
data_coco['categories'] = self.categories
data_coco['annotations'] = self.annotations
return data_coco
def save_json(self):
self.data_transfer()
self.data_coco = self.data2coco()
# 保存json文件
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder)
labelme_json = glob.glob('./Annotations/*.json')
labelme2coco(labelme_json, './json/test.json')或参考：https://github.com/open-mmlab/mmyolo/blob/main/docs/en/user_guides/custom_dataset.md
2.写yolov6、yolox的配置文件
新建一个名为 yolov6.py 的配置文件
新建位置自定，本人为：configs/custome/yolov6.py：
_base_ = '/home/work/mmyolo-dev/configs/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py'
max_epochs = 100
data_root = '/home/work/YOLO_presearch/20230130/' #coco数据地址
work_dir = './work_dirs/yolov6' #保存模型路径
#load_from = 'https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035-932e1d91.pth'#根据需要注释
train_batch_size_per_gpu = 4
train_num_workers = 4 # train_num_workers = nGPU x 4
save_epoch_intervals = 2
# base_lr_default * (your_bs / default_bs)
base_lr = 0.01 / 4
class_name = ('tou','chaxiao','ding','zd','noding')
num_classes = len(class_name)
metainfo = dict(
classes=class_name,
palette=[(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230), (106, 0, 228)])
train_cfg = dict(
max_epochs=max_epochs,
val_begin=20,
val_interval=save_epoch_intervals,
dynamic_intervals=[(max_epochs - _base_.num_last_epochs, 1)])
model = dict(
bbox_head=dict(head_module=dict(num_classes=num_classes)),
train_cfg=dict(
initial_assigner=dict(num_classes=num_classes),
assigner=dict(num_classes=num_classes)))
train_dataloader = dict(
batch_size=train_batch_size_per_gpu,
num_workers=train_num_workers,
dataset=dict(
_delete_=True,
type='RepeatDataset',
times=1,
dataset=dict(
type=_base_.dataset_type,
data_root=data_root,
metainfo=metainfo,
ann_file='annotations/train.json',
data_prefix=dict(img='images/'),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
pipeline=_base_.train_pipeline)))
val_dataloader = dict(
dataset=dict(
metainfo=metainfo,
data_root=data_root,
ann_file='annotations/val.json',
data_prefix=dict(img='images/')))
ann_file='annotations/val.json',
data_prefix=dict(img='images/')))
test_dataloader = val_dataloader
val_evaluator = dict(ann_file=data_root + 'annotations/val.json')
test_evaluator = val_evaluator
optim_wrapper = dict(optimizer=dict(lr=base_lr))
default_hooks = dict(
checkpoint=dict(
type='CheckpointHook',
interval=save_epoch_intervals,
max_keep_ckpts=5,
save_best='auto'),
param_scheduler=dict(max_epochs=max_epochs),
logger=dict(type='LoggerHook', interval=10))
custom_hooks = [
dict(
type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0001,
update_buffers=True,
strict_load=False,
priority=49),
dict(
type='mmdet.PipelineSwitchHook',
switch_epoch=max_epochs - _base_.num_last_epochs,
switch_pipeline=_base_.train_pipeline_stage2)
]新建一个名为 yolox.py 的配置文件
新建位置自定，本人为：configs/custome/yolox.py：
_base_ = '/home/work/mmyolo-dev/configs/yolox/yolox_m_fast_8xb8-300e_coco.py'
max_epochs = 100 # 训练的最大 epoch
data_root = '/home/work/YOLO_presearch/20230130/' # 数据集目录的绝对路径
work_dir = './work_dirs/yolox'
train_batch_size_per_gpu = 2
train_num_workers = 2
save_epoch_intervals = 2
base_lr = 0.01 / 4
anchors = [
[(68, 69), (154, 91), (143, 162)], # P3/8
[(242, 160), (189, 287), (391, 207)], # P4/16
[(353, 337), (539, 341), (443, 432)] # P5/32
]
class_name = ('tou','huan','chaxiao','ding','zd')
num_classes = len(class_name)
metainfo = dict(
classes=class_name,
palette=[(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230), (106, 0, 228)]
)
3、运行
