mxnet报错 Check failed: dshp.ndim() == 4U (3 vs. 4) : Input data should be 4D in batch-num_filter-y-x

报错：mxnet.base.MXNetError: Error in operator conv0: [17:40:27] src/operator/nn/convolution.cc:152: Check failed: dshp.ndim() == 4U (3 vs. 4) : Input data should be 4D in batch-num_filter-y-x

明明输入数据是4维的，为什么报错？

因为用collections.namedtuple装载数据，进行前向预测时，没有给data外面加上括号。也就是放在list里面

Batch = namedtuple("Batch",["data","label"])
label = 123
print('label',label)
label = mx.nd.array([label])
mod.forward(Batch([img],[label])) # 注意 Batch([img])的形式

参考

完整报错很吓人，问题很简单

Traceback (most recent call last):
  File "/home/user1/pjs/frvt/arcface_Siamese_offline/recognition/tools/eval_on_train_set.py", line 70, in <module>
    mod.forward(Batch(imgsNoMask))
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/module/module.py", line 625, in forward
    self.reshape(new_dshape, new_lshape)
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/module/module.py", line 472, in reshape
    self._exec_group.reshape(self._data_shapes, self._label_shapes)
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/module/executor_group.py", line 396, in reshape
    self.bind_exec(data_shapes, label_shapes, reshape=True)
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/module/executor_group.py", line 372, in bind_exec
    allow_up_sizing=True, **dict(data_shapes_i + label_shapes_i))
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/executor.py", line 458, in reshape
    ctypes.byref(handle)))
  File "/home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/base.py", line 253, in check_call
    raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: Error in operator conv0: [17:40:27] src/operator/nn/convolution.cc:152: Check failed: dshp.ndim() == 4U (3 vs. 4) : Input data should be 4D in batch-num_filter-y-x
Stack trace:
  [bt] (0) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x4b04cb) [0x7ff30319c4cb]
  [bt] (1) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x8eb956) [0x7ff3035d7956]
  [bt] (2) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x26206f2) [0x7ff30530c6f2]
  [bt] (3) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x2622f68) [0x7ff30530ef68]
  [bt] (4) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(mxnet::exec::GraphExecutor::Reshape(bool, bool, mxnet::Context const&, std::map<std::string, mxnet::Context, std::less<std::string>, std::allocator<std::pair<std::string const, mxnet::Context> > > const&, std::unordered_map<std::string, mxnet::TShape, std::hash<std::string>, std::equal_to<std::string>, std::allocator<std::pair<std::string const, mxnet::TShape> > > const&, std::vector<mxnet::NDArray, std::allocator<mxnet::NDArray> >*, std::vector<mxnet::NDArray, std::allocator<mxnet::NDArray> >*, std::vector<mxnet::NDArray, std::allocator<mxnet::NDArray> >*)+0x2a5) [0x7ff3052f9745]
  [bt] (5) /home/user1/miniconda3/envs/hardsample/lib/python2.7/site-packages/mxnet/libmxnet.so(MXExecutorReshapeEx+0x98c) [0x7ff305235bfc]
  [bt] (6) /home/user1/miniconda3/envs/hardsample/lib/python2.7/lib-dynload/../../libffi.so.7(+0x69dd) [0x7ff33b1679dd]
  [bt] (7) /home/user1/miniconda3/envs/hardsample/lib/python2.7/lib-dynload/../../libffi.so.7(+0x6067) [0x7ff33b167067]
  [bt] (8) /home/user1/miniconda3/envs/hardsample/lib/python2.7/lib-dynload/_ctypes.so(_ctypes_callproc+0x4de) [0x7ff33b1809de]