Error in operator custom1: [22:39:58]

[Feywell]

I want to implement a version which use complete resnet101 layers to learn RPN. But I get error like follows:

mxnet.base.MXNetError: Error in operator custom1: [22:39:58] src/operator/custom/custom.cc:153: Check failed: reinterpret_cast<CustomOpInferShapeFunc>( params.info->callbacks[kCustomOpPropInferShape])( shapes.size(), ndims.data(), shapes.data(), params.info->contexts[kCustomOpPropInferShape])

Stack trace returned 10 entries: [bt] (0) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x31f81a) [0x7f323127581a] [bt] (1) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x31fe41) [0x7f3231275e41] [bt] (2) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x487db1) [0x7f32313dddb1] [bt] (3) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x24de24a) [0x7f323343424a] [bt] (4) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x24e0b78) [0x7f3233436b78] [bt] (5) /home/feywell/anaconda3/envs/python2/lib/python2.7/site-packages/mxnet/libmxnet.so(MXSymbolInferShape+0x15aa) [0x7f32333b08ba] [bt] (6) /home/feywell/anaconda3/envs/python2/lib/python2.7/lib-dynload/../../libffi.so.6(ffi_call_unix64+0x4c) [0x7f3257b58ec0] [bt] (7) /home/feywell/anaconda3/envs/python2/lib/python2.7/lib-dynload/../../libffi.so.6(ffi_call+0x22d) [0x7f3257b5887d] [bt] (8) /home/feywell/anaconda3/envs/python2/lib/python2.7/lib-dynload/_ctypes.so(_ctypes_callproc+0x4de) [0x7f3257d6f8de] [bt] (9) /home/feywell/anaconda3/envs/python2/lib/python2.7/lib-dynload/_ctypes.so(+0x9b31) [0x7f3257d65b31]

How can i fix it? Thank you!