我怎样才能使用张量流对象检测来只检测人？
How can i use tensorflow object detection to only detect persons?
我一直在尝试使用 tensorflow 的对象检测来尝试设置一个体面的存在检测。我正在使用 tensorflow 的预训练模型和代码示例在网络摄像头上执行对象检测。有什么方法可以从模型中删除对象或从人物 class 中过滤掉对象吗？
这是我目前拥有的代码。
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from 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
# # Model preparation
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# 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 os.path.exists(MODEL_NAME + '/frozen_inference_graph.pb'):
print ('Downloading the model')
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())
print ('Download complete')
else:
print ('Model already exists')
# ## 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 maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
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)
#intializing the web camera device
import cv2
cap = cv2.VideoCapture(0)
# Running the tensorflow session
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
ret = True
while (ret):
ret,image_np = cap.read()
image_np = cv2.resize(image_np,(600,400))
# 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')
b = [x for x in classes if x == 1]
# 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(b).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
#print (len(boxes.shape))
#print (classes)
final_score = np.squeeze(scores)
count = 0
for i in range(100):
if scores is None or final_score[i] > 0.5:
count = count + 1
print (count, ' object(s) detected...')
# plt.figure(figsize=IMAGE_SIZE)
# plt.imshow(image_np)
cv2.imshow('image',image_np)
if cv2.waitKey(200) & 0xFF == ord('q'):
cv2.destroyAllWindows()
cap.release()
break
我看到您在行 b = [x for x in classes if x == 1] 中使用了过滤器来获取所有人员检测。 （在标签图中，person 的 id 正好是 1）。但它不起作用，因为您需要相应地更改 boxes、scores 和 classes。试试这个：
首先删除行
b = [x for x in classes if x == 1]
然后在sess.run()函数后添加如下内容
boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes)
indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices])
scores = np.squeeze(scores[indices])
classes = np.squeeze(classes[indices])
然后调用可视化函数
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
boxes,
classes,
scores,
category_index,
use_normalized_coordinates=True,
line_thickness=8)
想法是该模型可以检测多个 class 人，但只选择 class 个人在图像上可视化。
When the detected class is the only one,
I suggest this method to prevent loss of array.
# Select specific class
boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes).astype(np.int32)
indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices], axis=1) # to prevent errors made by nd.array of size 1 nd.array
scores = np.squeeze(scores[indices], axis=1)
classes = np.squeeze(classes[indices], axis=1)
我一直在尝试使用 tensorflow 的对象检测来尝试设置一个体面的存在检测。我正在使用 tensorflow 的预训练模型和代码示例在网络摄像头上执行对象检测。有什么方法可以从模型中删除对象或从人物 class 中过滤掉对象吗？ 这是我目前拥有的代码。
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from 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
# # Model preparation
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# 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 os.path.exists(MODEL_NAME + '/frozen_inference_graph.pb'):
print ('Downloading the model')
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())
print ('Download complete')
else:
print ('Model already exists')
# ## 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 maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
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)
#intializing the web camera device
import cv2
cap = cv2.VideoCapture(0)
# Running the tensorflow session
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
ret = True
while (ret):
ret,image_np = cap.read()
image_np = cv2.resize(image_np,(600,400))
# 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')
b = [x for x in classes if x == 1]
# 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(b).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
#print (len(boxes.shape))
#print (classes)
final_score = np.squeeze(scores)
count = 0
for i in range(100):
if scores is None or final_score[i] > 0.5:
count = count + 1
print (count, ' object(s) detected...')
# plt.figure(figsize=IMAGE_SIZE)
# plt.imshow(image_np)
cv2.imshow('image',image_np)
if cv2.waitKey(200) & 0xFF == ord('q'):
cv2.destroyAllWindows()
cap.release()
break
我看到您在行 b = [x for x in classes if x == 1] 中使用了过滤器来获取所有人员检测。 （在标签图中，person 的 id 正好是 1）。但它不起作用，因为您需要相应地更改 boxes、scores 和 classes。试试这个：
首先删除行
b = [x for x in classes if x == 1]
然后在sess.run()函数后添加如下内容
boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes)
indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices])
scores = np.squeeze(scores[indices])
classes = np.squeeze(classes[indices])
然后调用可视化函数
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
boxes,
classes,
scores,
category_index,
use_normalized_coordinates=True,
line_thickness=8)
想法是该模型可以检测多个 class 人，但只选择 class 个人在图像上可视化。
When the detected class is the only one, I suggest this method to prevent loss of array.
# Select specific class
boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes).astype(np.int32)
indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices], axis=1) # to prevent errors made by nd.array of size 1 nd.array
scores = np.squeeze(scores[indices], axis=1)
classes = np.squeeze(classes[indices], axis=1)