Python OpenCV 未显示对象检测张量流的结果

Question

#!/usr/bin/env python
# coding: utf-8

# # Object Detection API Demo


import os
import pathlib


if "models" in pathlib.Path.cwd().parts:
  while "models" in pathlib.Path.cwd().parts:
    os.chdir('..')
elif not pathlib.Path('models').exists():
  get_ipython().system('git clone --depth 1 https://github.com/tensorflow/models')


import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import cv2

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


# Import the object detection module.

# In[5]:


from object_detection.utils import ops as utils_ops
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util


# Get a reference to webcam 
video_capture = cv2.VideoCapture(0)
# Patches:

# In[6]:


# patch tf1 into `utils.ops`
utils_ops.tf = tf.compat.v1

# Patch the location of gfile
tf.gfile = tf.io.gfile


# # Model preparation 

# ## Variables
# 
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing the path.
# 
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/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.

# ## Loader

# In[7]:


def load_model(model_name):
  base_url = 'http://download.tensorflow.org/models/object_detection/'
  model_file = model_name + '.tar.gz'
  model_dir = tf.keras.utils.get_file(
    fname=model_name, 
    origin=base_url + model_file,
    untar=True)

  model_dir = pathlib.Path(model_dir)/"saved_model"

  model = tf.saved_model.load(str(model_dir))
  model = model.signatures['serving_default']

  return model


# ## 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

# In[8]:


# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = 'models/research/object_detection/data/mscoco_label_map.pbtxt'
category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)


# For the sake of simplicity we will test on 2 images:

# In[9]:


# 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 = pathlib.Path('models/research/object_detection/test_images')
TEST_IMAGE_PATHS = sorted(list(PATH_TO_TEST_IMAGES_DIR.glob("*.jpg")))
TEST_IMAGE_PATHS


# # Detection

# Load an object detection model:

# In[10]:


model_name = 'ssd_mobilenet_v1_coco_2017_11_17'
detection_model = load_model(model_name)


# Check the model's input signature, it expects a batch of 3-color images of type uint8: 

# In[11]:


print(detection_model.inputs)


# And retuns several outputs:

# In[12]:


detection_model.output_dtypes


# In[13]:


print(detection_model.output_shapes)


# Add a wrapper function to call the model, and cleanup the outputs:

# In[14]:


def run_inference_for_single_image(model, image):
  image = np.asarray(image)
  # The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
  input_tensor = tf.convert_to_tensor(image)
  # The model expects a batch of images, so add an axis with `tf.newaxis`.
  input_tensor = input_tensor[tf.newaxis,...]

  # Run inference
  output_dict = model(input_tensor)

  # All outputs are batches tensors.
  # Convert to numpy arrays, and take index [0] to remove the batch dimension.
  # We're only interested in the first num_detections.
  num_detections = int(output_dict.pop('num_detections'))
  output_dict = {key:value[0, :num_detections].numpy() 
                 for key,value in output_dict.items()}
  output_dict['num_detections'] = num_detections

  # detection_classes should be ints.
  output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)

  # Handle models with masks:
  if 'detection_masks' in output_dict:
    # Reframe the the bbox mask to the image size.
    detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
              output_dict['detection_masks'], output_dict['detection_boxes'],
               image.shape[0], image.shape[1])      
    detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5,
                                       tf.uint8)
    output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()

  return output_dict


# Run it on each test image and show the results:

# In[15]:



# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.

# Grab a single frame of video
while True:
  ret, image_np = video_capture.read()
  # Actual detection.
  output_dict = run_inference_for_single_image(detection_model, image_np)
  # 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_reframed', None),
      use_normalized_coordinates=True,
      line_thickness=8)

  cv2.imshow('Detected',image_np)
  if cv2.waitKey(25) & 0xFF == ord('q'):
      cv2.destroyAllWindows()
      break

我添加了用于从网络摄像头进行对象检测的代码，当我运行此代码时，它会显示检测 2 - 5 秒，然后在 imshow 窗口中显示无响应。

注意：

• 我也用过 cv2.waitKey(1)，cv2.waitKey(0)，结果一样。

• 我正在使用 tensorflow-gpu，它检测到我的 GPU：1050ti。

• 但是 OpenCV 使用 CPU 来显示图像。

更新部分：

while True:
  ret, image_np = video_capture.read()
  if ret == False:
    break
  # Actual detection.
  output_dict = run_inference_for_single_image(detection_model, image_np)
  # 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_reframed', None),
      use_normalized_coordinates=True,
      line_thickness=8)

  cv2.imshow('Detected',image_np)
  if cv2.waitKey(0) & 0xFF == ord('q'):
      break

cv2.destroyAllWindows()
video_capture.release()

[已解决] 我刚刚创建了新的 conda 环境并安装了 tensorflow 版本 TF v1.15.2 并使用来自https://pythonprogramming.net/video-tensorflow-object-detection-api-tutorial/ 链接的代码。

现在它可以工作了，但是代码包含一些不推荐使用的功能。

Answer 1

使用以下函数调用的返回值。

ret, image_np = video_capture.read()
if ret == False:
    break

另外，将 cv2.destroyAllWindows() 移到 while 条件之外。

while True:
    #your code here

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

cv2.destroyAllWindows()