Question

我已经用niftynet训练了一个模型，没有任何错误，但是当我运行推理命令时，就会出现问题。

CRITICAL:niftynet: unknown output format: shape (10, 1) spatial dims are: ()
Traceback (most recent call last):
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/engine/application_driver.py", line 275, in run_application
    self._inference_loop(session, loop_status)
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/engine/application_driver.py", line 493, in _inference_loop
    self._loop(iter_generator(itertools.count(), INFER), sess, loop_status)
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/engine/application_driver.py", line 442, in _loop
    iter_msg.current_iter_output[NETWORK_OUTPUT])
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/application/segmentation_application.py", line 390, in interpret_output
    batch_output['window'], batch_output['location'])
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/engine/windows_aggregator_grid.py", line 42, in decode_batch
    window, location = self.crop_batch(window, location, self.window_border)
  File "/Users/qinyangshou/anaconda3/lib/python3.6/site-packages/niftynet/engine/windows_aggregator_base.py", line 135, in crop_batch
    raise NotImplementedError
NotImplementedError

我认为我的配置文件有问题，但是我不知道在哪里修改。

未知的输出格式：形状（10，1）空间变暗为：（）

0 个答案: