errors while call the keras.applications.inception_v3

[heroxrq]

I turn my keras backend from tensorflow to mxnet to use mxnet's multi gpu training. However the code I run successfully in keras tensorflow backend seems not compatible with keras mxnet backend. It prints the following:

Using MXNet backend.
train and valid generator is ok
steps_per_epoch: 55673
validation_steps: 1236
Traceback (most recent call last):
File "train_inception_v3_transfer_learning.py", line 64, in
base_model = InceptionV3(include_top=False, weights=None, input_shape=(3, INPUT_HEIGHT, INPUT_WIDTH))
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/applications/inception_v3.py", line 151, in InceptionV3
(3, 3), strides=(1, 1), border_mode='same')(x)
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 572, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 166, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/layers/pooling.py", line 160, in call
dim_ordering=self.dim_ordering)
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/layers/pooling.py", line 251, in _pooling_function
border_mode, dim_ordering, pool_mode='avg')
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/backend/mxnet_backend.py", line 33, in func_wrapper
train_ret = func(*args, **kwargs)
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/keras/backend/mxnet_backend.py", line 2912, in pool2d
stride=strides)
File "", line 39, in Pooling
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/mxnet/_ctypes/symbol.py", line 127, in _symbol_creator
ctypes.byref(sym_handle)))
File "/home/xierenqiang/install/anaconda3/lib/python3.6/site-packages/mxnet/base.py", line 129, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: Invalid Input: 'same', valid values are: {'full', 'valid'}, in operator Pooling(name="", stride="(1, 1)", pooling_convention="same", pool_type="avg", kernel="(3, 3)")

[DSLituiev]

I am getting an error even without specifying input shape with this two simple lines:

from keras.applications.inception_v3 import InceptionV3
#Using MXNet backend.
base_model = InceptionV3(weights='imagenet',
                               include_top=False,
                                #pooling=None,
                               )

error:

[21:10:59] /home/travis/build/dmlc/mxnet-distro/mxnet-build/dmlc-core/include/dmlc/logging.h:308: [21:10:59] src/operator/./pooling-inl.h:214: Check failed: param_.kernel[0] <= dshape[2] + 2 * param_.pad[0] kernel size (3) exceeds input (0 padded to 0)

Stack trace returned 10 entries:
[bt] (0) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xec23c) [0x7fec5a44123c]
[bt] (1) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x1170ca2) [0x7fec5b4c5ca2]
[bt] (2) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xf90817) [0x7fec5b2e5817]
[bt] (3) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16e9531) [0x7fec5ba3e531]
[bt] (4) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16ead42) [0x7fec5ba3fd42]
[bt] (5) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16eb686) [0x7fec5ba40686]
[bt] (6) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16d4e88) [0x7fec5ba29e88]
[bt] (7) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xe049fe) [0x7fec5b1599fe]
[bt] (8) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xe0732e) [0x7fec5b15c32e]
[bt] (9) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(MXSymbolInferShape+0x156f) [0x7fec5b154d2f]

------------------------------------------------------------------------
MXNetError                             Traceback (most recent call last)
<ipython-input-2-8dfe2d4abb60> in <module>()
      1 base_model = InceptionV3(weights='imagenet',
----> 2                             include_top=False,
      3                             #pooling=None,
      4                             )
      5

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/applications/inception_v3.py in InceptionV3(include_top, weights, input_tensor, input_shape, classes)
    133     x = MaxPooling2D((3, 3), strides=(2, 2))(x)
    134
--> 135     x = conv2d_bn(x, 80, 1, 1, border_mode='valid')
    136     x = conv2d_bn(x, 192, 3, 3, border_mode='valid')
    137     x = MaxPooling2D((3, 3), strides=(2, 2))(x)

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/applications/inception_v3.py in conv2d_bn(x, nb_filter, nb_row, nb_col, border_mode, subsample, name)
     56                       activation='relu',
     57                       border_mode=border_mode,
---> 58                       name=conv_name)(x)
     59     x = BatchNormalization(axis=bn_axis, name=bn_name)(x)
     60     return x

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/engine/topology.py in __call__(self, x, mask)
    527             # Raise exceptions in case the input is not compatible
    528             # with the input_spec specified in the layer constructor.
--> 529             self.assert_input_compatibility(x)
    530
    531             # Collect input shapes to build layer.

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/engine/topology.py in assert_input_compatibility(self, input)
    462                                          str(K.ndim(x)))
    463                 else:
--> 464                     if K.ndim(x) != spec.ndim:
    465                         raise ValueError('Input ' + str(input_index) +
    466                                          ' is incompatible with layer ' +

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/backend/mxnet_backend.py in ndim(x)
    632     ```
    633     """
--> 634     s = shape(x)
    635     if s is None:
    636         return 0

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/backend/mxnet_backend.py in shape(x)
    577     #       return tuple([0 if x is None else x for x in x._keras_shape])
    578     if isinstance(x, KerasSymbol):
--> 579         return x.get_shape()
    580     else:
    581         return None

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/keras/backend/mxnet_backend.py in get_shape(self)
    256             return self.tensor.shape
    257         else:
--> 258             _, out_shape, _ = self.symbol.infer_shape_partial()
    259             return out_shape[0]
    260

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/symbol.py in infer_shape_partial(self, *args, **kwargs)
   1048             The order is same as the order of list_auxiliary_states().
   1049         """
-> 1050         return self._infer_shape_impl(True, *args, **kwargs)
   1051
   1052     def _infer_shape_impl(self, partial, *args, **kwargs):

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/symbol.py in _infer_shape_impl(self, partial, *args, **kwargs)
   1105             ctypes.byref(aux_shape_ndim),
   1106             ctypes.byref(aux_shape_data),
-> 1107             ctypes.byref(complete)))
   1108         if complete.value != 0:
   1109             arg_shapes = [

~/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/base.py in check_call(ret)
    127     """
    128     if ret != 0:
--> 129         raise MXNetError(py_str(_LIB.MXGetLastError()))
    130
    131 if sys.version_info[0] < 3:

MXNetError: Error in operator pooling0: [21:10:59] src/operator/./pooling-inl.h:214: Check failed: param_.kernel[0] <= dshape[2] + 2 * param_.pad[0] kernel size (3) exceeds input (0 padded to 0)

Stack trace returned 10 entries:
[bt] (0) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xec23c) [0x7fec5a44123c]
[bt] (1) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x1170ca2) [0x7fec5b4c5ca2]
[bt] (2) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xf90817) [0x7fec5b2e5817]
[bt] (3) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16e9531) [0x7fec5ba3e531]
[bt] (4) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16ead42) [0x7fec5ba3fd42]
[bt] (5) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16eb686) [0x7fec5ba40686]
[bt] (6) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x16d4e88) [0x7fec5ba29e88]
[bt] (7) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xe049fe) [0x7fec5b1599fe]
[bt] (8) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(+0xe0732e) [0x7fec5b15c32e]
[bt] (9) /home/ubuntu/anaconda3/envs/mxnet/lib/python3.5/site-packages/mxnet/libmxnet.so(MXSymbolInferShape+0x156f) [0x7fec5b154d2f]

[sandeep-krishnamurthy]

Will look in to this.