mxnet train multi-label error

最新推荐文章于 2021-03-26 11:10:58 发布

jinggegebuaa

最新推荐文章于 2021-03-26 11:10:58 发布

阅读量2k

点赞数

本文链接：https://blog.csdn.net/keyanxiaocaicai/article/details/53213188

版权

ggj@ggj-All-Series:~/ggj/pro/end-to-end-for-chinese-plate-recognition-master$ python train.py
here
here2
[10:11:57] src/io/iter_image_recordio.cc:211: ImageRecordIOParser: /home/ggj/ggj/data/carplant/carplant.rec, use 3 threads for decoding..
[10:11:57] src/io/iter_image_recordio.cc:211: ImageRecordIOParser: /home/ggj/ggj/data/carplant/carplant.rec, use 3 threads for decoding..
get_iterator() finished
[10:11:58] src/operator/./reshape-inl.h:249: Using target_shape will be deprecated.
Traceback (most recent call last):
File "train.py", line 111, in <module>
    train();
File "train.py", line 105, in train
    model.fit(X = data_train, eval_data = data_test, eval_metric = Accuracy, batch_end_callback=mx.callback.Speedometer(batch_size, 50))
File "/home/ggj/ggj/pro/mxnet/python/mxnet/model.py", line 745, in fit
    self._init_params(dict(data.provide_data+data.provide_label))
File "/home/ggj/ggj/pro/mxnet/python/mxnet/model.py", line 485, in _init_params
    arg_shapes, _, aux_shapes = self.symbol.infer_shape(**input_shapes)
File "/home/ggj/ggj/pro/mxnet/python/mxnet/symbol.py", line 453, in infer_shape
    return self._infer_shape_impl(False, *args, **kwargs)
File "/home/ggj/ggj/pro/mxnet/python/mxnet/symbol.py", line 513, in _infer_shape_impl
    ctypes.byref(complete)))
File "/home/ggj/ggj/pro/mxnet/python/mxnet/base.py", line 77, in check_call
    raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: InferShape Error in softmax's label argument