I am trying to run the this image classification example that uses Mxnet library in python and the pre-trained deep learning model Inception-BN. The execution throws and error on this line: prob = model.predict(batch)[0] with the error message:
MXNetError: InferShape Error in ch_concat_3c_chconcat: [14:35:56] src/operator/./concat-inl.h:152: Check failed: (dshape[j]) == (tmp[j]) Incorrect shape[2]: (1,320,15,15). (first input shape: (1,576,14,14))
I tried downloading the Inception-BN model again to make sure it was up to date but it didn't make a difference. I do suspect the problem could be on line: model = mx.model.FeedForward.load(prefix, num_round, ctx=mx.gpu(), numpy_batch_size=1) where I had to change gpu for cpu since my server is not equiped with a gpu. Nevertheless the error doesn't seem to point on that direction.
Any idea how to fix it? Is using a cpu instead of a gpu a problem other than a lower performance?
Finally here is the complete error information:
---------------------------------------------------------------------------
MXNetError Traceback (most recent call last)
<ipython-input-7-98e51e4226e1> in <module>()
1 # Get prediction probability of 1000 classes from model
----> 2 prob = model.predict(batch)[0]
3 # Argsort, get prediction index from largest prob to lowest
4 pred = np.argsort(prob)[::-1]
5 # Get top1 label
/users/CREATE/olb/mxnet/python/mxnet/model.pyc in predict(self, X, num_batch, return_data, reset)
589 data_shapes = X.provide_data
590 data_names = [x[0] for x in data_shapes]
--> 591 self._init_predictor(data_shapes)
592 batch_size = X.batch_size
593 data_arrays = [self._pred_exec.arg_dict[name] for name in data_names]
/users/CREATE/olb/mxnet/python/mxnet/model.pyc in _init_predictor(self, input_shapes)
520 # for now only use the first device
521 pred_exec = self.symbol.simple_bind(
--> 522 self.ctx[0], grad_req='null', **dict(input_shapes))
523 pred_exec.copy_params_from(self.arg_params, self.aux_params)
524
/users/CREATE/olb/mxnet/python/mxnet/symbol.pyc in simple_bind(self, ctx, grad_req, type_dict, **kwargs)
623 if type_dict is None:
624 type_dict = {k: mx_real_t for k in self.list_arguments()}
--> 625 arg_shapes, _, aux_shapes = self.infer_shape(**kwargs)
626 arg_types, _, aux_types = self.infer_type(**type_dict)
627 if arg_shapes == None or arg_types == None:
/users/CREATE/olb/mxnet/python/mxnet/symbol.pyc in infer_shape(self, *args, **kwargs)
410 The order is in the same order as list_auxiliary()
411 """
--> 412 return self._infer_shape_impl(False, *args, **kwargs)
413
414 def infer_shape_partial(self, *args, **kwargs):
/users/CREATE/olb/mxnet/python/mxnet/symbol.pyc in _infer_shape_impl(self, partial, *args, **kwargs)
470 ctypes.byref(aux_shape_ndim),
471 ctypes.byref(aux_shape_data),
--> 472 ctypes.byref(complete)))
473 if complete.value != 0:
474 arg_shapes = [
/users/CREATE/olb/mxnet/python/mxnet/base.pyc in check_call(ret)
75 """
76 if ret != 0:
---> 77 raise MXNetError(py_str(_LIB.MXGetLastError()))
78
79 def c_str(string):
MXNetError: InferShape Error in ch_concat_3c_chconcat: [14:35:56] src/operator/./concat-inl.h:152: Check failed: (dshape[j]) == (tmp[j]) Incorrect shape[2]: (1,320,15,15). (first input shape: (1,576,14,14))
