Question

我正在尝试为“校园建筑探测器”运行我的代码，并且我正在使用Tensorflow的对象检测api和faster_rcnn_inception_v2作为模型。我已经对该网络进行了7000次训练（耗时12小时），并且由于迭代次数更多（我有900000）而中止，现在当我尝试运行代码时，出现以下错误：

无法为形状为（（？，？，？，3）'的张量'image_tensor：0'输入形状（480，640，3）的值

我正在使用anaconda，Jupiter Notebook，Python v3.6.8，Tensorflow v1.13.1

代码：

import cv2
cap = cv2.VideoCapture(0)
try:
    with detection_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)

                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, 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'):
                        cap.release()
                        cv2.destroyAllWindows()
                        break
except Exception as e:
    print(e)
    cap.release()

谢谢。

Answer 1

函数run_inference_for_single_image期望成批输入图像（四个维度），因此下面的行尝试将三个维度的图像扩展为四个，

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

您只需要更改行

output_dict = run_inference_for_single_image(image_np, detection_graph)

进入

output_dict = run_inference_for_single_image(image_np_expanded, detection_graph)

那将解决问题。

无法为形状为（（？，？，？，3）'的张量'image_tensor：0'输入形状（480，640，3）的值

1 个答案: