0 
input_tensors=["import/image_tensor:0"],
output_tensors=['import/detection_boxes:0', 'import/detection_scores:0',
                        'import/detection_classes:0', 'import/num_detections:0']

_input = [graph.get_tensor_by_name(tensor_name) for tensor_name in input_tensors]
_output_ops = [graph.get_tensor_by_name(tensor_name) for tensor_name in output_tensors]
sess = tf.Session(graph=graph, config=_config_proto)

image_expanded = np array of size specific to model (1, 512, 512, 1)

(boxes, scores, classes, num_detections) = sess.run(self._output_ops, feed_dict={_input: image_expanded})

当我运行 sess.run 时出现错误

-------------------------------------------------- ------------------------- TypeError Traceback (最近一次调用最后一次) in 3 image_np = load_image_into_numpy_array(image) 4 image_np_expanded = np.expand_dims(image_np, axis=0) ----> 5 (boxes, scores, classes, num_detections) = sess.run(_output_ops, feed_dict={_input: image_np_expanded}) 6 print(boxes) 7 break

类型错误：不可散列类型：“列表”

4

1 回答 1

0

在这种情况下，_input 是一个列表。所以 sess.run 应该有 _input[0]

(boxes, scores, classes, num_detections) = sess.run(self._output_ops, feed_dict={_input[0]: image_expanded})
于 2020-12-30T06:27:37.630 回答