物体检测YOLOv3实践

物体检测是计算机视觉中的一个重要的研究领域，在人流检测，行人跟踪，自动驾驶，医学影像等领域有着广泛的应用。不同于简单的图像分类，物体检测旨在对图像中的目标进行精确识别，包括物体的位置和分类，因此能够应用于更多高层视觉处理的场景。例如在自动驾驶领域，需要辨识摄像头拍摄的图像中的车辆、行人、交通指示牌及其位置，以便进一步根据这些数据决定驾驶策略。本期学习案例，我们将聚焦于YOLO算法，YOLO(You Only Look Once)是一种one-stage物体检测算法。

注意事项：

1. 本案例使用框架: TensorFlow-1.13.1

2. 本案例使用硬件规格: GPU V100

3. 进入运行环境方法：点此链接进入AI Gallery，点击Run in ModelArts按钮进入ModelArts运行环境，如需使用GPU,您可以在ModelArts JupyterLab运行界面右边的工作区进行切换

4. 运行代码方法: 点击本页面顶部菜单栏的三角形运行按钮或按Ctrl+Enter键 运行每个方块中的代码

5. JupyterLab的详细用法: 请参考《ModelAtrs JupyterLab使用指导》

6. 碰到问题的解决办法: 请参考《ModelAtrs JupyterLab常见问题解决办法》

1.数据和代码下载

运行下面代码，进行数据和代码的下载和解压

本案例使用coco数据，共80个类别。

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")

2.准备数据

2.1文件路径定义

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)

Using TensorFlow backend.
/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.

  _np_qint8 = np.dtype([("qint8", np.int8, 1)])

/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.

  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])

/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])

2.2读取标注数据

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

2.3数据读取函数，构建数据生成器。每次读取一个批次的数据至内存训练，并做数据增强。

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)

3.模型训练

本案例使用Keras深度学习框架搭建YOLOv3神经网络。

可以进入相应的文件夹路径查看源码实现。

3.1构建神经网络

可以在./yolo3/model.py文件中查看细节

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)

WARNING:tensorflow:From /home/ma-user/anaconda3/envs/TensorFlow-1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.

# 打印模型各层结构
model.summary()

(此处代码执行的输出很长，省略)

训练回调函数定义

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

3.2开始训练

from keras.optimizers import Adam
from yolo3.utils import get_random_data 

# 设置所有的层可训练
for i in range(len(model.layers)):
    model.layers[i].trainable = True
    
# 选择Adam优化器，设置学习率
learning_rate = 1e-4
model.compile(optimizer=Adam(lr=learning_rate), loss={'yolo_loss': lambda y_true, y_pred: y_pred}) 

# 设置批大小和训练轮数
batch_size = 16
max_epochs = 2
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
# 开始训练
model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, data_path,anchors, num_classes),
    steps_per_epoch=max(1, num_train//batch_size),
    validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, data_path,anchors, num_classes),
    validation_steps=max(1, num_val//batch_size),
    epochs=max_epochs,
    initial_epoch=0,
    callbacks=[reduce_lr, early_stopping])

Train on 179 samples, val on 19 samples, with batch size 16.



Epoch 1/2



11/11 [==============================] - 25s 2s/step - loss: 46.6694 - val_loss: 39.1381



Epoch 2/2



11/11 [==============================] - 5s 452ms/step - loss: 45.5145 - val_loss: 43.6707





<keras.callbacks.History at 0x7fbff60659e8>

3.3保存模型

import os
if not os.path.exists(save_path):
    os.makedirs(save_path)
    # 保存模型
    model.save_weights(os.path.join(save_path, 'trained_weights_final.h5'))

4.模型测试

4.1打开一张测试图片

from PIL import Image
import numpy as np
# 测试文件路径
test_file_path = './test.jpg'
# 打开测试文件
image = Image.open(test_file_path)
image_ori = np.array(image)
image_ori.shape

(640, 481, 3)

4.2图片预处理

from yolo3.utils import letterbox_image

new_image_size = (image.width - (image.width % 32), image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
image_data /= 255.
image_data = np.expand_dims(image_data, 0)
image_data.shape

(1, 640, 480, 3)

import keras.backend as K
sess = K.get_session()

4.3构建模型

from yolo3.model import yolo_body
from keras.layers import Input
# coco数据anchor值文件存储位置
anchor_path = "./model_data/yolo_anchors.txt"
with open(anchor_path) as f:
    anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
anchors = np.array(anchors).reshape(-1, 2)
yolo_model = yolo_body(Input(shape=(None,None,3)), len(anchors)//3, num_classes)

4.4加载模型权重，或将模型路径替换成上一步训练得出的模型路径

# 模型权重存储路径
weights_path = "./model_data/yolo.h5"
yolo_model.load_weights(weights_path)

4.5定义IOU以及score：

• IOU： 将交并比大于IOU的边界框作为冗余框去除
• score：将预测分数大于score的边界框筛选出来

iou = 0.45
score = 0.8

4.6构建输出[boxes, scores, classes]

from yolo3.model import yolo_eval
input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(
    yolo_model.output, 
    anchors,
    num_classes,
    input_image_shape,
    score_threshold=score, 
    iou_threshold=iou)

4.7进行预测

out_boxes, out_scores, out_classes = sess.run(
    [boxes, scores, classes],
    feed_dict={
        yolo_model.input: image_data,
        input_image_shape: [image.size[1], image.size[0]],
        K.learning_phase(): 0
    })

class_coco = get_classes(classes_path)
out_coco = []
for i in out_classes:
    out_coco.append(class_coco[i])

print(out_boxes)
print(out_scores)
print(out_coco)

[[152.69937  166.2726   649.0503   459.9374  ]



 [ 68.62158   21.843088 465.66208  452.6878  ]]



[0.9838943 0.999688 ]



['person', 'umbrella']

4.8将预测结果绘制在图片上

from PIL import Image, ImageFont, ImageDraw

font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
                    size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))

thickness = (image.size[0] + image.size[1]) // 300

for i, c in reversed(list(enumerate(out_coco))):
    predicted_class = c
    box = out_boxes[i]
    score = out_scores[i]

    label = '{} {:.2f}'.format(predicted_class, score)
    draw = ImageDraw.Draw(image)
    label_size = draw.textsize(label, font)

    top, left, bottom, right = box
    top = max(0, np.floor(top + 0.5).astype('int32'))
    left = max(0, np.floor(left + 0.5).astype('int32'))
    bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
    right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
    print(label, (left, top), (right, bottom))

    if top - label_size[1] >= 0:
        text_origin = np.array([left, top - label_size[1]])
    else:
        text_origin = np.array([left, top + 1])

    for i in range(thickness):
        draw.rectangle(
            [left + i, top + i, right - i, bottom - i],
            outline=225)
    draw.rectangle(
        [tuple(text_origin), tuple(text_origin + label_size)],
        fill=225)
    draw.text(text_origin, label, fill=(0, 0, 0), font=font)
    del draw

umbrella 1.00 (22, 69) (453, 466)



person 0.98 (166, 153) (460, 640)

image