核心ML模型转换失败，并显示“模型应具有一个准确的输出（概率），以自动将其分类。”

Question

当尝试将此链接here中的caffe模型zoo转换为core ml模型时，收到以下错误： RuntimeError：模型应该只有一个输出（概率），可以自动将其分类。

================= Summary of the conversion: ===================================
Detected input(s) and shape(s) (ignoring batch size):
'data' : 3, 227, 227

Network Input name(s): 'data'.
Network Output name(s): 'loss1/SLclassifier', 'loss2/SLclassifier', 'loss3/SLclassifier'.

Traceback (most recent call last):
  File "convert.py", line 7, in <module>
    class_labels='class_labels.txt')
  File "/anaconda2/lib/python2.7/site-packages/coremltools/converters/caffe/_caffe_converter.py", line 191, in convert
    predicted_feature_name)
  File "/anaconda2/lib/python2.7/site-packages/coremltools/converters/caffe/_caffe_converter.py", line 255, in _export
    predicted_feature_name)
RuntimeError: Model should have exactly one output (the probabilities) to automatically make it a classifier.

您可以在所附的屏幕截图中看到我的代码库。

如何解决此错误？

enter image description here