物体检测YOLOv3实践

import os
from modelarts.session import Session
sess = Session()

if sess.region_name == 'cn-north-1':
    bucket_path="modelarts-labs/notebook/DL_object_detection_yolo/yolov3.tar.gz"
elif sess.region_name == 'cn-north-4':
    bucket_path="modelarts-labs-bj4/notebook/DL_object_detection_yolo/yolov3.tar.gz"
else:
    print("请更换地区到北京一或北京四")

if not os.path.exists('./yolo3'):
    sess.download_data(bucket_path=bucket_path, path="./yolov3.tar.gz")

if os.path.exists('./yolov3.tar.gz'):
    # 解压文件
    os.system("tar -xf ./yolov3.tar.gz")

    # 清理压缩包
    os.system("rm -r ./yolov3.tar.gz")

from train import get_classes, get_anchors
# 数据文件路径
data_path = "./coco/coco_data"
# coco类型定义文件存储位置
classes_path = './model_data/coco_classes.txt'
# coco数据anchor值文件存储位置
anchors_path = './model_data/yolo_anchors.txt'
# coco数据标注信息文件存储位置
annotation_path = './coco/coco_train.txt'
# 预训练权重文件存储位置
weights_path = "./model_data/yolo.h5"
# 模型文件存储位置
save_path = "./result/models/"

classes = get_classes(classes_path)
anchors = get_anchors(anchors_path)
# 获取类型数量和anchor数量变量
num_classes = len(classes)
num_anchors = len(anchors)

import numpy as np

# 训练集与验证集划分比例
val_split = 0.1
with open(annotation_path) as f:
    lines = f.readlines()
np.random.seed(10101)
np.random.shuffle(lines)
np.random.seed(None)
num_val = int(len(lines)*val_split)
num_train = len(lines) - num_val

def data_generator(annotation_lines, batch_size, input_shape, data_path,anchors, num_classes):
    n = len(annotation_lines)
    i = 0
    while True:
        image_data = []
        box_data = []
        for b in range(batch_size):
            if i==0:
                np.random.shuffle(annotation_lines)
            image, box = get_random_data(annotation_lines[i], input_shape, data_path,random=True) # 随机挑选一个批次的数据
            image_data.append(image)
            box_data.append(box)
            i = (i+1) % n
        image_data = np.array(image_data)
        box_data = np.array(box_data)
        y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes) # 对标注框预处理，过滤异常标注框
        yield [image_data, *y_true], np.zeros(batch_size)

def data_generator_wrapper(annotation_lines, batch_size, input_shape, data_path,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, data_path,anchors, num_classes)

import keras.backend as K
from yolo3.model import preprocess_true_boxes, yolo_body, yolo_loss
from keras.layers import Input, Lambda
from keras.models import Model
# 初始化session
K.clear_session()

# 图像输入尺寸
input_shape = (416, 416)
image_input = Input(shape=(None, None, 3))
h, w = input_shape
# 设置多尺度检测的下采样尺寸
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)]

# 构建YOLO模型结构
model_body = yolo_body(image_input, num_anchors//3, num_classes)

# 将YOLO权重文件加载进来，如果希望不加载预训练权重，从头开始训练的话，可以删除这句代码
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)

# 定义YOLO损失函数
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])

# 构建Model，为训练做准备
model = Model([model_body.input, *y_true], model_loss)

# 打印模型各层结构
model.summary()

from keras.callbacks import ReduceLROnPlateau, EarlyStopping

# 定义回调方法
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3, verbose=1) # 学习率衰减策略
early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1) # 早停策略