ricky10116r2d2的部落格

TensorFlow object_detection API的安装

https://blog.csdn.net/sarsscofy/article/details/81111815 (主要)

https://blog.gtwang.org/programming/tensorflow-object-detection-api-tutorial/

===============

#一定要保存为UTF8的格式哦
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import matplotlib
import cv2
 
# Matplotlib chooses Xwindows backend by default.
matplotlib.use('Agg')
 
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
#from utils import label_map_util
#from utils import visualization_utils as vis_util
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
 
 
##################### Download Model，如果本地已下载也可修改成本地路径
# 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 if not already downloaded
if not os.path.exists(PATH_TO_CKPT):
    print('Downloading model... (This may take over 5 minutes)')
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    print('Extracting...')
    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())
else:
    print('Model already downloaded.')
 
##################### Load a (frozen) Tensorflow model into memory.
print('Loading model...')
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
print('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)
 
##################### Detection
# 测试图片的路径，可以根据自己的实际情况修改
TEST_IMAGE_PATH = 'test_images/image1.jpg'
 
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
 
print('Detecting...')
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    print(TEST_IMAGE_PATH)
    image = Image.open(TEST_IMAGE_PATH)
    image_np = load_image_into_numpy_array(image)
    image_np_expanded = np.expand_dims(image_np, axis=0)
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
    boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
    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)
    print(TEST_IMAGE_PATH.split('.')[0]+'_labeled.jpg')
    plt.figure(figsize=IMAGE_SIZE, dpi=300)
    # 不知道为什么，在我的机器上没显示出图片，有知道的朋友指点下，谢谢
    plt.imshow(image_np)
    # 保存标记图片
    plt.savefig(TEST_IMAGE_PATH.split('.')[0] + '_labeled.jpg')