成功解决(wait)KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operatio

成功解决(wait)KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operatio

解决问题

KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph."

全部代码

#run_inference_for_single_image(image, graph) #函数实现单张图像的推断
def run_inference_for_single_image(image, graph):
  with graph.as_default():
#     detection_graph = tf.Graph()
    with tf.Session() as sess:  #graph=detection_graph
      # 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'
      ]: #score每个检测结果的confidence、classes每个框所对应的类别、num_detections框检测的个数
        tensor_name = key + ':0'
        if tensor_name in all_tensor_names:
          tensor_dict[key] = detection_graph.get_tensor_by_name(
              tensor_name)
      if 'detection_masks' in tensor_dict:
        # The following processing is only for single image
        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
        detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
        # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
        real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
        detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) #boxes变量存放了所有检测框
        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[0], image.shape[1])
        detection_masks_reframed = tf.cast(
            tf.greater(detection_masks_reframed, 0.5), tf.uint8)
        # Follow the convention by adding back the batch dimension
        tensor_dict['detection_masks'] = tf.expand_dims(
            detection_masks_reframed, 0)
      print(tf.get_default_graph())
      image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') #image_tensor:0

      # Run inference 使用sess.run真正开始计算
      output_dict = sess.run(tensor_dict,
                             feed_dict={image_tensor: np.expand_dims(image, 0)})

      # all outputs are float32 numpy arrays, so convert types as appropriate
      output_dict['num_detections'] = int(output_dict['num_detections'][0])
      output_dict['detection_classes'] = output_dict[
          'detection_classes'][0].astype(np.uint8)
      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

#6、for循环实现预测并绘制检测后的图片
for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image) #将图片草转换为numpy形式
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0) #将图片扩展一个维度，最后进入神经网络的格式应该为[1,?,?,3]
  # 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)
  plt.figure(figsize=IMAGE_SIZE)
  plt.title('TFOD API Official Case Tutorial——Jason Niu')
  plt.imshow(image_np)

解决方法

prediction = tf.nn.softmax(tf.matmul(last,weight)+bias, name="prediction")
y_pred = graph.get_tensor_by_name("Reshape_1:0")

for op in graph.get_operations():
    print(op.name)

1、解决方法来自Stackoverflow

外国朋友的解决的方法，其内容比较详细，我就不再抛砖引玉了，欢迎大家留言探讨！

哈哈，最后，博主，成功搞定！

相关文章

KeyError : The tensor variable , Refer to the tensor which does not exists

how to predict with .meta and checkpoint files in tensorflow?

赞 (0)

相关推荐