Python 网络摄像机上的自定义对象检测

我尝试在ubuntu 20上本地运行自定义人脸检测模型 但是当我运行脚本时，我得到了这个

Traceback (most recent call last):
  File "webcam_detection.py", line 104, in <module>
    cv2.imshow('object detection', cv2.resize(image_np, (1200,900)))
cv2.error: OpenCV(4.4.0) /tmp/pip-req-build-h2062vqd/opencv/modules/highgui/src/window.cpp:651: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage'

---

看起来您的OpenCV安装没有任何GUI支持，您是如何安装OpenCV及其python绑定的？您的问题的答案非常清楚。使用Windows、GTK+2.x或Cocoa支持重建库。如果您在Ubuntu或Debian上，请安装libgtk2.0-dev和pkg-config，然后在函数“cvShowImage”中重新运行cmake或配置脚本

######## Object Detection for Image #########
# 
# Author: Khai Do
# Date: 9/3/2019

## Some parts of the code is copied from Tensorflow object detection
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb


# Import libraries
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import zipfile
import cv2
import tensorflow.compat.v1 as tf

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

# Define the video stream
cap = cv2.VideoCapture(0)  # Change only if you have more than one webcams

# What model
directPath = os.getcwd()
print(directPath)
MODEL_NAME = 'fine_tune_graph'

# 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', 'object-detection.pbtxt')
# Number of classes to detect
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.size
    return np.array(image.getdata()).reshape(
        (im_height, im_width, 3)).astype(np.uint8)


# Detection
with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        while True:

            # Read frame from camera
            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)
            # Extract image tensor
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            # Extract detection boxes
            boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
            # Extract detection scores
            scores = detection_graph.get_tensor_by_name('detection_scores:0')
            # Extract detection classes
            classes = detection_graph.get_tensor_by_name('detection_classes:0')
            # Extract number of detectionsd
            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=8)

            # Display output
            cv2.imshow('object detection', cv2.resize(image_np, (1200,900)))

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