TensorFlow models - object detection API 安装

tensorflow 的 models 模块非常有用，不仅实现了各种模型，也包括了原作者训练好的模型及其使用方法，本文以 object detection 为例来说明如何使用训练好的模型；

首先呢，还是建议去官网看看使用方法，因为 tensorflow 的版本混乱，网上教程针对的版本各不相同，所以各种坑；

下面是正题，本文针对 windows 操作系统；

第一步：下载 models 模块，解压

https://github.com/tensorflow/models

第二步：安装 protoc

https://github.com/protocolbuffers/protobuf/releases 从这里下载，选择适合自己的版本；

下载后复制到 models 所在的文件夹下，解压，生成 bin、include；

将 bin 下的 protoc.exe 复制到 C:\Windows\System32 文件夹下；

cmd 运行 protoc，出现如下界面，说明安装成功；

第三步：编译 protoc

在 models/research 下运行 Windows PowerShell 　　　　　　　　　　　　　　【运行 PowerShell】

运行命令

protoc object_detection/protos/*.proto --python_out=.

运行完成后，检查 object_detection/protos 文件夹，如果每个 proto 文件都变成了 py 文件，表示编译成功

第四步：添加环境变量

添加这两个目录

...\models\research
...\models\research\slim

至于怎么添加，你可以用常规的设置环境变量的方式，官方是 PYTHONPATH；

网上有添加 .pth 文件，我实验未成功；

第五步：测试 API 是否安装成功

python object_detection/builders/model_builder_test.py

出现上图表示成功；

第六步：执行已经训练好的模型

执行 object_detection/object_detection_tutorial.ipynb 文件　　　　【执行方法我的博客】

或者自己写

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image


# # This is needed to display the images.
# %matplotlib inline

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
sys.path.append("../..")
print(sys.path)

# from utils import label_map_util
# from utils import visualization_utils as vis_util
from research.object_detection.utils import label_map_util
from research.object_detection.utils import visualization_utils as vis_util

# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

# download model
# opener = urllib.request.URLopener()
# print(DOWNLOAD_BASE + MODEL_FILE)
# opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
    file_name = os.path.basename(file.name)
    if 'frozen_inference_graph.pb' in file_name:
        tar_file.extract(file, os.getcwd())

# Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')
# Loading label map
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
                                                            use_display_name=True)
category_index = label_map_util.create_category_index(categories)


# Helper code
def load_image_into_numpy_array(image):
    (im_width, im_height) = image.size
    return np.array(image.getdata()).reshape(
        (im_height, im_width, 3)).astype(np.uint8)


# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3)]

# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)

with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        # Definite input and output Tensors for detection_graph
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
        # Each box represents a part of the image where a particular object was detected.
        detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
        # Each score represent how level of confidence for each of the objects.
        # Score is shown on the result image, together with the class label.
        detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
        detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
        for image_path in TEST_IMAGE_PATHS:
            image = Image.open(image_path)
            # the array based representation of the image will be used later in order to prepare the
            # result image with boxes and labels on it.
            image_np = load_image_into_numpy_array(image)
            # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
            image_np_expanded = np.expand_dims(image_np, axis=0)
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            # Each box represents a part of the image where a particular object was detected.
            boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
            # Each score represent how level of confidence for each of the objects.
            # Score is shown on the result image, together with the class label.
            scores = detection_graph.get_tensor_by_name('detection_scores:0')
            classes = detection_graph.get_tensor_by_name('detection_classes:0')
            num_detections = 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,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=8)
            Image.fromarray(image_np).save('%sob.jpg'%image_path)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()