python实现目标检测_入门指南：用Python实现实时目标检测（内附代码）

import numpy as np

import os

import six.moves.urllib as urllib

import sys

import tarfile

import tensorflow as tf

import zipfile

from distutils.version import StrictVersion

from collections import defaultdict

from io import StringIO

from matplotlib import pyplot as plt

from PIL import Image

# This isneeded since the notebook is stored in the object_detection folder.

sys.path.append("..")

from utils import ops as utils_ops

if StrictVersion(tf.__version__)

[2]:

# This isneeded to display the images.

get_ipython().run_line_magic( matplotlib , inline )

[3]:

# Objectdetection imports

# Here arethe imports from the object detection module.

from utils import label_map_util

from utils import visualization_utils as vis_util

[4]:

# Modelpreparation

# Anymodel exported using the `export_inference_graph.py` tool can be loaded heresimply by changing `PATH_TO_FROZEN_GRAPH` to point to a new .pb file.

# Bydefault we use an "SSD with Mobilenet" model here.

#See https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

#for alist of other models that can be run out-of-the-box with varying speeds andaccuracies.

# Whatmodel to download.

MODEL_NAME= ssd_mobilenet_v1_coco_2017_11_17

MODEL_FILE= MODEL_NAME + .tar.gz

DOWNLOAD_BASE= http://download.tensorflow.org/models/object_detection/

# Path tofrozen detection graph. This is the actual model that is used for the objectdetection.

PATH_TO_FROZEN_GRAPH= MODEL_NAME + /frozen_inference_graph.pb

# List ofthe strings that is used to add correct label for each box.

PATH_TO_LABELS= os.path.join( data , mscoco_label_map.pbtxt )

[5]:

#DownloadModel

opener =urllib.request.URLopener()

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())

[6]:

# Load a(frozen) Tensorflow model into memory.

detection_graph= tf.Graph()

with detection_graph.as_default():

od_graph_def= tf.GraphDef()

withtf.gfile.GFile(PATH_TO_FROZEN_GRAPH, rb ) as fid:

serialized_graph= fid.read()

od_graph_def.ParseFromString(serialized_graph)

tf.import_graph_def(od_graph_def,name= )

[7]:

# Loadinglabel map

# Labelmaps map indices to category names, so that when our convolution networkpredicts `5`,

#we knowthat this corresponds to `airplane`. Here we use internal utilityfunctions,

#butanything that returns a dictionary mapping integers to appropriate stringlabels would be fine

category_index= label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS,use_display_name=True)

[8]:

defrun_inference_for_single_image(image, graph):

with graph.as_default():

with tf.Session() as sess:

# Get handles to input and output tensors

ops= tf.get_default_graph().get_operations()

all_tensor_names= {output.name for op in ops for output in op.outputs}

tensor_dict= {}

for key in [

num_detections , detection_boxes , detection_scores ,

detection_classes , detection_masks ]:

tensor_name= key + :0

if tensor_name in all_tensor_names:

tensor_dict[key]= tf.get_default_graph().get_tensor_by_name(tensor_name)

if detection_masks in tensor_dict:

# The following processing is only for single image

detection_boxes= tf.squeeze(tensor_dict[ detection_boxes ], [0])

detection_masks= tf.squeeze(tensor_dict[ detection_masks ], [0])

# Reframe is required to translate mask from boxcoordinates to image coordinates and fit the image size.

real_num_detection= tf.cast(tensor_dict[ num_detections ][0], tf.int32)

detection_boxes= tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])

detection_masks= tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])

detection_masks_reframed= utils_ops.reframe_box_masks_to_image_masks(

detection_masks,detection_boxes, image.shape[1],image.shape[2])

detection_masks_reframed= tf.cast(

tf.greater(detection_masks_reframed,0.5),tf.uint8)

# Follow the convention by adding back the batchdimension

tensor_dict[ detection_masks ] =tf.expand_dims(

detection_masks_reframed,0)

image_tensor= tf.get_default_graph().get_tensor_by_name( image_tensor:0 )

# Run inference

output_dict= sess.run(tensor_dict, feed_dict={image_tensor: image})

# all outputs are float32 numpy arrays, so convert typesas appropriate

output_dict[ num_detections ] =int(output_dict[ num_detections ][0])

output_dict[ detection_classes ] =output_dict[

detection_classes ][0].astype(np.int64)

output_dict[ detection_boxes ] =output_dict[ detection_boxes ][0]

output_dict[ detection_scores ] =output_dict[ detection_scores ][0]

if detection_masks in output_dict:

output_dict[ detection_masks ] =output_dict[ detection_masks ][0]

return output_dict

[9]:

import cv2

cam =cv2.cv2.VideoCapture(0)

rolling = True

while (rolling):

ret,image_np = cam.read()

image_np_expanded= np.expand_dims(image_np, axis=0)

# Actual detection.

output_dict= run_inference_for_single_image(image_np_expanded, detection_graph)

# Visualization of the results of a detection.

vis_util.visualize_boxes_and_labels_on_image_array(

image_np,

output_dict[ detection_boxes ],

output_dict[ detection_classes ],

output_dict[ detection_scores ],

category_index,

instance_masks=output_dict.get( detection_masks ),

use_normalized_coordinates=True,

line_thickness=8)

cv2.imshow( image , cv2.resize(image_np,(1000,800)))

if cv2.waitKey(25) & 0xFF == ord( q ):

break

cv2.destroyAllWindows()

cam.release()

在运行Jupyter notebook时，网络摄影系统会开启并检测所有原始模型训练过的物品类别。

来源：Pexels

感谢阅读本文，如果有什么建议，欢迎在留言区积极发言哟~

推荐阅读专题

留言 点赞 发个朋友圈

我们一起分享AI学习与发展的干货

编译组：

蔡思齐、孙梦琪

相关链接：

https://hackernoon.com/introductory-guide-to-real-time-object-detection-with-python-6jyb36t5

如需转载，请后台留言，遵守转载规范

推荐文章阅读