训练自己的数据进行目标检测
0.建立相关的目录
在项目根目录下新建VOCdevkit\VOC2007\Annotations
、VOCdevkit\VOC2007\ImageSets\Main
、VOCdevkit\VOC2007\JPEGImages
、logs\000
四个目录
1. 使用标注工具labelimg
标注数据
链接:https://pan.baidu.com/s/1SO4NqNSfXyKMNCGQA-4LVQ 提取码:ydqi
- 标注数据
open dir 选择需要标注的数据目录,change save dir 选择要保存的目录VOCdevkit\VOC2007\Annotations
,use default label 勾选,填写一个标签名称,create Rectbox 标注数据,保存即可,如下图
数据标注完成以后,会在VOCdevkit\VOC2007\Annotations
目录下生成相关的.xml
文件
2. 生成训练集测试集验证集
- 在
VOC2007
目录下新建一个dataShape.py
文件,目的是用来分割数据,运行此文件会在VOCdevkit\VOC2007\ImageSets\Main
目录下生成test.txt train.txt trainval.txt val.txt
四个文件,dataShape.py
文件代码如下:
import os
import random
trainval_percent = 0.2
train_percent = 0.8
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()
3.生成yolo3所需的train.txt,val.txt,test.txt
生成的数据集不能供yolov3直接使用。需要运行voc_annotation.py ,classes以检测一个类为例(眼睛),在voc_annotation.py需改你的数据集为:
classes = ["eye"]
运行python voc_annotation.py
会生成 2007_train.txt``2007_test.txt``2007_val.txt
,把这三个txt文件分别改名为 train.txt``test.txt``val.txt
利用voc制作自己的数据集
4.修改参数文件yolo3.cfg
打开yolo3.cfg文件。搜索yolo(共出现三次),每次按下图都要修改
[convolutional]
size=1
stride=1
pad=1
# filters:3*(5+len(classes));<===> 3*(5+1)
filters=18
activation=linear
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
# classes: len(classes) = 1,这里是"eye"一类
classes=1
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
# random:改为0
random=0
5.修改model_data下的voc_classes.txt为自己训练的类别
eye
6.生成yolo_anchors.txt
文件
运行 python kmeans.py
,会在根目录下生成yolo_anchors.txt
文件,剪切到 model_data
目录下
7.修改train.py代码(用下面代码直接替换原来的代码)
因为 train.py会报错。本人电脑 win10家庭版.坑死人了
"""
Retrain the YOLO model for your own dataset.
"""
import numpy as np
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping
from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss
from yolo3.utils import get_random_data
def _main():
annotation_path = '2007_train.txt'
log_dir = 'logs/000/'
classes_path = 'model_data/voc_classes.txt'
anchors_path = 'model_data/yolo_anchors.txt'
class_names = get_classes(classes_path)
anchors = get_anchors(anchors_path)
input_shape = (416,416) # multiple of 32, hw
model = create_model(input_shape, anchors, len(class_names) )
train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir)
def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):
model.compile(optimizer='adam', loss={
'yolo_loss': lambda y_true, y_pred: y_pred})
logging = TensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(log_dir + "ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5",
monitor='val_loss', save_weights_only=True, save_best_only=True, period=1)
batch_size = 10
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.shuffle(lines)
num_val = int(len(lines)*val_split)
num_train = len(lines) - num_val
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes),
steps_per_epoch=max(1, num_train//batch_size),
validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors, num_classes),
validation_steps=max(1, num_val//batch_size),
epochs=500,
initial_epoch=0)
model.save_weights(log_dir + 'trained_weights.h5')
def get_classes(classes_path):
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def get_anchors(anchors_path):
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False,
weights_path='model_data/yolo_weights.h5'):
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
num_anchors//3, num_classes+5)) for l in range(3)]
model_body = yolo_body(image_input, num_anchors//3, num_classes)
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print('Load weights {}.'.format(weights_path))
if freeze_body:
# Do not freeze 3 output layers.
num = len(model_body.layers)-7
for i in range(num): model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))
model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
np.random.shuffle(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
i %= n
image, box = get_random_data(annotation_lines[i], input_shape, random=True)
image_data.append(image)
box_data.append(box)
i += 1
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def data_generator_wrap(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
if n==0 or batch_size<=0: return None
return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)
if __name__ == '__main__':
_main()
8.生成模型
运行python train.py
,会在 logs\000
下生成日志文件和trained_weights_stage_1.h5
模型文件
9.测试训练效果
把生成的trained_weights_stage_1.h5
模型文件,改为yolo.h5
,放在 model_data
目录下,运行 python yolo_video.py --image
,输入图片路径,查看测试效果
2020.01.02 20:54