? 使用anaconda3， 先安装
? 换源，若不然会非常慢 方式参考 https://www.cnblogs.com/Dean0731/p/11560371.html
? export PATH="/usr/local/anaconda3/bin:$PATH"
? 新建虚拟环境 本例python=3.5
? 进入环境本例安装的tensorflow=1.14.0
? 安装其他依赖包,pillow,lxml 等，亦可以等待报错时安装相应模块
注：train 训练集，trainval 训练集中的测试集，val 测试集
# 生成objection——detection/protos 下的py文件 models/research 目录下
protoc object_detection/protos/*.proto --python_out=.
# 运行完成后，可以检查object_detection/protos/文件夹，如果每个proto文件都成了对应的以py为后缀的python源码，就说明编译成功了
# 添加环境变量：export PYTHONPATH=$PYTHONPATH:/home/dzf/models/research:/home/dzf/models/research/slim准备：VOC2012 解压后的数据 VOCdevkit
生成数据
# 可能需要pillow，lxml等包
# data_dir voc目录 即为解压后文件夹
# year 接收VOC2007 VOC2012
# set 表示使用train训练
# output_path 生成的文件路径
# 可能会报错 data/pascal_label_map.pbtxt 找不到 移到上级目录运行即可
python create_pascal_tf_record.py
--set=train或val 表示时生成训练数据还是测试数据
--data_dir=.../VOCdevkit
--year=VOC2012 默认 VOC2007
--output_path=..../训练文件.record（pascal_train.record）
pascal_train.record # 生成的训练数据
pascal_val.record # 生成的测试数据models：在objection_detection/sample/config/xxxxxx.config # models配置文件
包含训练次数，分类数，测试集，测试集标签，训练集，训练集标签的位置
重要：接其官方的训练结果 fine_tune_checkpoint: "下载的他人models解压后的文件夹/model.ckpt"
下载地址:https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md
注意下载的models要与你选择的model.config一致 本例为 faster_rcnn_inception_resnet_v2_atrous_coco 加压后有文件夹faster_rcnn_inception_resnet_v2_atrous_coco_2018_1_29
修改配置文件
# 指定接着训练的模型，若要重新开始注释本行，下行改为false即可
fine_tune_checkpoint: "D:\\\\faster_rcnn_inception_resnet_v2_atrous_coco_2018_1_29\\model.ckpt"
from_detection_checkpoint: true
# 训练集，训练集标签，测试集，测试集标签
input_path: "D:\\\pascal_train.record"
label_map_path: "D:\\data\\pascal_label_map.pbtxt"
input_path: "D:\\models\\pascal_val.record"
label_map_path: "D:\\models\\pascal_label_map.pbtxt"# 开始训练：cpu训练较慢，可在配置文件修改次数，若出现内存溢出，也可修改config中的图片大小600x1024，可改小一点
python legacy/train.py
--train_dir=/home/dzf/train # model # 输出目录
--pipeline_config_path=/home/dzf/dataset/models/faster_rcnn_inception_resnet_v2_atrous_coco.config # 配置文件
# 新版的models 是用的是object_detection/model_main.py --model_dir=.....
# 旧版的models 使用的是object_detection/train.py --train_dir=...
# 注意形参名称改变了，本例使用的是新版的models但使用的是legacy/train.pypython export_inference_graph.py
--input_type=image_tensor
--pipeline_config_path=/...../models/faster_rcnn_inception_resnet_v2_atrous_coco.config
--trained_checkpoint_prefix=/...../train/model.ckpt-10
--output_directory=/..../train注：上编的路径尽量使用绝对路径，不要使用相对路径和～符号 可能报错
生成frozen_inference_graph.pb文件 及其他文件
import cv2
import numpy as np
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
class TOD(object):
def __init__(self):
# self.PATH_TO_CKPT = '/home/dzf/train/frozen_inference_graph.pb'
self.PATH_TO_CKPT = '/home/dzf/dataset/models/faster_rcnn_inception_resnet_v2_atrous_coco_2018_01_28/frozen_inference_graph.pb'
#self.PATH_TO_CKPT = '/home/dzf/train_model/frozen_inference_graph.pb'
self.PATH_TO_LABELS = '/home/dzf/dataset/tools/pascal_label_map.pbtxt'
self.NUM_CLASSES = 20
self.detection_graph = self._load_model()
self.category_index = self._load_label_map()
def _load_model(self):
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(self.PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
return detection_graph
def _load_label_map(self):
label_map = label_map_util.load_labelmap(self.PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map,
max_num_classes=self.NUM_CLASSES,
use_display_name=True)
category_index = label_map_util.create_category_index(categories)
return category_index
def detect(self, image):
with self.detection_graph.as_default():
with tf.Session(graph=self.detection_graph) as sess:
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image, axis=0)
image_tensor = self.detection_graph.get_tensor_by_name('image_tensor:0')
boxes = self.detection_graph.get_tensor_by_name('detection_boxes:0')
scores = self.detection_graph.get_tensor_by_name('detection_scores:0')
classes = self.detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = self.detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
self.category_index,
use_normalized_coordinates=True,
line_thickness=8)
cv2.namedWindow("detection", cv2.WINDOW_NORMAL)
cv2.imshow("detection", image)
cv2.waitKey(0)
if __name__ == '__main__':
#image = cv2.imread('/home/dzf/dataset/VOCdevkit/VOC2012/JPEGImages/2007_000027.jpg')
#image = cv2.imread('/home/dzf/Downloads/aeroplane.jpeg')
image = cv2.imread('/home/dzf/Downloads/people.jpg')
detecotr = TOD()
detecotr.detect(image)
# 本例中在原始模型训练的基础上的训练一定次数 生成model.ckpt 之后转为pb文件 进行目标检测 没有检测框
# 若使用原始模型的pb文件 faster_rcnn_inception_resnet_v2_atrous_coco_2018_1_29/frozen_interence_inception.pb 可以显示检测框，至于什么原因还没有找到原文：https://www.cnblogs.com/Dean0731/p/11924302.html