keras-yolo3-master使用记录
keras-yolo3-master使用记录
- 源码下载 环境配置 快速测试
- 制作自己的项目
- 生成yolo3所需的train.txt,val.txt,test.txt
- 修改model_data下的文件，放入你的类别，coco,voc这两个文件都需要修改。
- 训练自己的网络
你好！ 这是你第一次使用 Markdown编辑器 所展示的欢迎页。如果你想学习如何使用Markdown编辑器, 可以仔细阅读这篇文章，了解一下Markdown的基本语法知识。
源码下载 环境配置 快速测试
在macos windows liunx系统都测试过，本文采用macos
-
项目代码：https://github.com/qqwweee/keras-yolo3
-
下载yolo3weights ：https://pjreddie.com/darknet/yolo/
将yolo3weights文件夹放到keras-yolo3-master文件夹里
-
terminal cd 到keras-yolo3-master文件夹
生成现在权重下h5文件：
python3 convert.py yolov3.cfg yolov3.weights model_data/yolo.h5 -
进行快速测试，看看能不能用。
terminal cd到keras-yolo3-master目录下
python3 yolo_video.py --image
之后让你输入图片路径：（若将图片放在keras-yolo3-master文件夹下，直接输入相对地址即可）
制作自己的项目
-
下载VOC2007数据集
下载地址： https://pjreddie.com/projects/pascal-voc-dataset-mirror/ -
这里面用到的文件夹是Annotation、ImageSets和JPEGImages
其中文件夹Annotation中主要存放xml文件，每一个xml对应一张图像在这里插入图片描述；而ImageSets我们只需要用到Main文件夹，这里面存放的是一些文本文件，通常为train.txt、test.txt等，该文本文件里面的内容是需要用来训练或测试的图像的名字；JPEGImages文件夹中放我们已按统一规则命名好的原始图像。
将自己数据转移到对应目录
// 将自己原始图片，标注过的图片放到VOC数据集相应位置，并生成训练集测试集验证集
//生成训练集测试集验证集对应txt文件，放入相应位置
#%%
import os
import random
import shutil #拷贝文件并移动的库
path = '/code/kaggle/wechat/' #自己的数据路径
img = os.listdir(path + 'pyq') #所有原始图像
img_xml = os.listdir(path + 'labeled') #所有xml文件
print('img_num: ',len(img))
print('img_xml_num: ',len(img_xml))
#清空VOC数据集文件夹内容
path_img_ori = '/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/JPEGImages'
path_xml = '/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/Annotations'
img_ = os.listdir(path_img_ori)
xml_ = os.listdir(path_xml)
for img__ in img_:
os.remove(os.path.join(path_img_ori,img__))
for xml__ in xml_:
os.remove(os.path.join(path_xml,xml__))
#生成VOC数据集文件夹内容
k = 0
for i in range(len(img)):
path_img_ori = '/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/JPEGImages/'
path_xml = '/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/Annotations/'
#拷贝转移文件，并按0，1，2命名新文件
#shutil.copyfile（old——path， new-path）
shutil.copyfile(path + 'pyq/' + img[i] , path_img_ori + str(k) + '.' + 'jpg')
shutil.copyfile(path + 'labeled/' + img_xml[i] , path_xml + str(k) + '.' + img_xml[i].split('.')[-1])
context.append(str(k))
k = k+1
trainval_percent = 0.2
train_percent = 0.8 #自己定比例
xmlfilepath = path_xml
txtsavepath = '/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/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)
#到达的文件路径～/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt'
ftrainval = open('/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt', 'w')
ftest = open('/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/ImageSets/Main/test.txt', 'w')
ftrain = open('/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/ImageSets/Main/train.txt', 'w')
fval = open('/code/kaggle/keras-yolo3-master/VOCdevkit/VOC2007/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()
#%%
生成yolo3所需的train.txt,val.txt,test.txt
打开keras-yolo3-master文件夹下voc_annatation.py文件进行修改
import xml.etree.ElementTree as ET
from os import getcwd
sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
classes = ["dz_tx"] #这里改为自己标注数据集中的标签名
def convert_annotation(year, image_id, list_file):
in_file = open('/code/keras-yolo3-master/VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id),'rb')
tree=ET.parse(in_file)
root = tree.getroot()
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 = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
wd = getcwd()
for year, image_set in sets:
image_ids = open('/code/keras-yolo3-master/VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
list_file = open('%s.txt'%( image_set), 'w')
for image_id in image_ids:
list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, year, image_id))
convert_annotation(year, image_id, list_file)
list_file.write('\n')
list_file.close()
修改model_data下的文件，放入你的类别，coco,voc这两个文件都需要修改。
一个标签占一行
训练自己的网络
直接复制替换原来train.py即可
此时自己在keras-yolo3-master下新建文件夹logs logs下再建文件夹000
-
run时可能会报错
AttributeError: module ‘keras.backend’ has no attribute ‘control_flow_ops’解决办法：https://blog.csdn.net/CAU_Ayao/article/details/89312354
-
可能Tensorboard报错
我发现Tensorboard这行代码是灰色的，所以我把它作为释义不用了 -
建议先将epoch调小一些进行测试
"""
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 = '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})
#################这个位置#######################
#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()