在谷歌 Colab 中使用 cv2.imshow()

Question

我正在尝试通过输入视频来对视频进行对象检测

cap = cv2.VideoCapture("video3.mp4")

在处理部分之后，我想使用实时对象检测显示视频

while True:
ret, image_np = cap.read()

# 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.
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('object detection', cv2.resize(image_np, (800, 600)))
if cv2.waitKey(25) & 0XFF == ord('q'):
    cv2.destroyAllWindows()
    break

但是 colab 说 cv2.imshow() 被禁用并使用 cv2_imshow()。但它只渲染图像。[一帧一帧]。我想像使用 cv2.imshow() 那样将视频输出。请帮我解决这个问题。提前致谢。

附上我的完整代码

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

import cv2
from google.colab.patches import cv2_imshow

cap = cv2.VideoCapture("video3.mp4")

sys.path.append("..")
from object_detection.utils import ops as utils_ops

if StrictVersion(tf.__version__) < StrictVersion('1.12.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.12.*.')

from object_detection.utils import label_map_util

from object_detection.utils import visualization_utils as vis_util

detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.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='')


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


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)


PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(3, 8) ]

IMAGE_SIZE = (12, 8)

def run_inference_for_single_image(image, graph):
with graph.as_default():
with tf.Session() as sess:

  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:

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

    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)

    tensor_dict['detection_masks'] = tf.expand_dims(
        detection_masks_reframed, 0)
  image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')


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


  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

while True:
    ret, image_np = cap.read()

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

    output_dict = run_inference_for_single_image(image_np_expanded, detection_graph)

    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_np)
if cv2.waitKey(25) & 0XFF == ord('q'):
    cv2.destroyAllWindows()
    break

Answer 1

要cv2.imshow在 google colab 中使用，您可以使用以下导入：

from google.colab.patches import cv2_imshow
cv2_imshow(img)

Answer 2

这个Colab笔记本提供了一种在笔记本上观看视频的方法：

import io
import base64
from IPython.display import HTML

def playvideo(filename):
    video = io.open(filename, 'r+b').read()
    encoded = base64.b64encode(video)
    return HTML(data='''<video alt="test" controls>
                    <source src="data:video/mp4;base64,{0}" type="video/mp4"/>
                 </video>'''.format(encoded.decode('ascii')))

然后观看视频使用playvideo('./Megamind.mp4')。

不管怎样，记得把它放在%pylab notebook笔记本的开头，这对解决此类问题有很大帮助。