本文主要是介绍TensorFlow：将自己训练好的模型迁移到电脑摄像头和外置海康摄像头上,并在视频中实时检测，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
有了训练好的模型之后，可以将模型迁移到电脑或者手机上
电脑：
# -*- coding: utf-8 -*-
"""@author: Terry n
"""
# Imports
import numpy as np
import os
import sys
import tensorflow as tf
import cv2# if tf.__version__ < '1.4.0':
# raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')os.chdir('D:\\object_detection_api\\models-master\\research\\object_detection')# Env setup
# 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("..")# Object detection imports
from utils import label_map_utilfrom utils import visualization_utils as vis_util# Model preparation
# What model to download.
#MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17' # [30,21] best
# MODEL_NAME = 'ssd_inception_v2_coco_2017_11_17' #[42,24]
# MODEL_NAME = 'faster_rcnn_inception_v2_coco_2017_11_08' #[58,28]
# MODEL_NAME = 'faster_rcnn_resnet50_coco_2017_11_08' #[89,30]
# MODEL_NAME = 'faster_rcnn_resnet50_lowproposals_coco_2017_11_08' #[64, ]
# MODEL_NAME = 'rfcn_resnet101_coco_2017_11_08' #[106,32]
# MODEL_NAME = 'faster_rcnn_inception_resnet_v2_atrous_coco_2018_01_28'
# MODEL_NAME = 'ssdlite_mobilenet_v2_coco_2018_05_09'
MODEL_NAME = 'fod_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')
PATH_TO_LABELS = os.path.join('data', 'fod.pbtxt')#NUM_CLASSES = 90
NUM_CLASSES = 1
# 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.sizereturn np.array(image.getdata()).reshape((im_height, im_width, 3)).astype(np.uint8)# 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_graphimage_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')# the video to be detected, eg, "test.mp4" herevidcap = cv2.VideoCapture(0)# Default resolutions of the frame are obtained.The default resolutions are system dependent.# We convert the resolutions from float to integer.frame_width = int(vidcap.get(3))frame_height = int(vidcap.get(4))while (True):ret, image = vidcap.read()if ret == True:# image_np = load_image_into_numpy_array(image)image_np = 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)# Actual detection.(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_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(scores)cv2.imshow("capture",image_np)if cv2.waitKey(1) & 0xFF == ord('q'):ret = False# Break the loopelse:break
vidcap.release()
cv2.destroyAllWindows()注意：1，第十八行定位到你的object_detection文件夹下。
2，43行，47行定位到模型位置。50,51行相继修改。54行num_classes为1
3，注意，将此model_video的python文件定位到object_detection下，再在anaconda下运行。
海康摄像头：
model_video.py
# -*- coding: utf-8 -*-
"""@author: Terry n
"""
# Imports
import numpy as np
import os
import sys
import tensorflow as tf
import cv2# if tf.__version__ < '1.4.0':
# raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')os.chdir('D:\\object_detection_api\\models-master\\research\\object_detection')# Env setup
# 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("..")# Object detection imports
from utils import label_map_utilfrom utils import visualization_utils as vis_util# Model preparation
# What model to download.
#MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17' # [30,21] best
# MODEL_NAME = 'ssd_inception_v2_coco_2017_11_17' #[42,24]
# MODEL_NAME = 'faster_rcnn_inception_v2_coco_2017_11_08' #[58,28]
# MODEL_NAME = 'faster_rcnn_resnet50_coco_2017_11_08' #[89,30]
# MODEL_NAME = 'faster_rcnn_resnet50_lowproposals_coco_2017_11_08' #[64, ]
# MODEL_NAME = 'rfcn_resnet101_coco_2017_11_08' #[106,32]
# MODEL_NAME = 'faster_rcnn_inception_resnet_v2_atrous_coco_2018_01_28'
# MODEL_NAME = 'ssdlite_mobilenet_v2_coco_2018_05_09'
# MODEL_NAME = 'fod_detection'
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'# 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', 'fod.pbtxt')
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')NUM_CLASSES = 90
# NUM_CLASSES = 1
# 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.sizereturn np.array(image.getdata()).reshape((im_height, im_width, 3)).astype(np.uint8)# 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_graphimage_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')# the video to be detected, eg, "test.mp4" hereurl = 'rtsp://admin:ha515515@192.168.1.64:554/11'# vidcap = cv2.VideoCapture(0)# Default resolutions of the frame are obtained.The default resolutions are system dependent.# We convert the resolutions from float to integer.while (True):vidcap = cv2.VideoCapture(url)ret, image = vidcap.read()frame_width = int(vidcap.get(3))frame_height = int(vidcap.get(4))if ret == True:# image_np = load_image_into_numpy_array(image)image_np = 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)# Actual detection.(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_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(scores)cv2.imshow("capture",image_np)if cv2.waitKey(20) & 0xFF == ord('q'):ret = False# Break the loopelse:break
vidcap.release()
cv2.destroyAllWindows()3，在视频中实时检测
video_detection.py
# By Terry_n
# https://space.bilibili.com/275177832
# 可以放在任何文件夹下运行（前提正确配置API[环境变量]）
# 输出视频没有声音，pr可解决一切import numpy as np
import os
import sys
import tensorflow as tf
import cv2
import timefrom object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_utilstart = time.time()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
cv2.setUseOptimized(True) # 加速cv# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")# 可能要改的内容
######################################################
PATH_TO_CKPT = 'D:\\object_detection_api\\models-master\\research\\object_detection\\fod_detection\\fod_frozen_inference_graph.pb' # 模型及标签地址PATH_TO_LABELS = 'D:\\object_detection_api\\models-master\\research\\object_detection\\data\\fod.pbtxt'video_PATH = "D:\\object_detection_api\\models-master\\research\\object_detection\\test_video\\cycling.mp4" # 要检测的视频
out_PATH = "D:\\object_detection_api\\models-master\\research\\object_detection\\output_video\\out_cycling1.mp4" # 输出地址NUM_CLASSES = 1 # 检测对象个数fourcc = cv2.VideoWriter_fourcc(*'DIVX') # 编码器类型（可选）
# 编码器： DIVX , XVID , MJPG , X264 , WMV1 , WMV2####################################################### 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)# 读取视频
video_cap = cv2.VideoCapture(video_PATH)
fps = int(video_cap.get(cv2.CAP_PROP_FPS)) # 帧率width = int(video_cap.get(3)) # 视频长，宽
hight = int(video_cap.get(4))videoWriter = cv2.VideoWriter(out_PATH, fourcc, fps, (width, hight))config = tf.ConfigProto()
config.gpu_options.allow_growth = True # 减小显存占用
with detection_graph.as_default():with tf.Session(graph=detection_graph, config=config) as sess:# Definite input and output Tensors for detection_graphimage_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')num = 0while True:ret, frame = video_cap.read()if ret == False: # 没检测到就跳出breaknum += 1print(num) # 输出检测到第几帧了# print(num/fps) # 检测到第几秒了image_np = frameimage_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=4)# 写视频videoWriter.write(image_np)videoWriter.release()
end = time.time()
print("Execution Time: ", end - start)
这篇关于TensorFlow：将自己训练好的模型迁移到电脑摄像头和外置海康摄像头上,并在视频中实时检测的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
