Error with mxnet backend

I get the following error when trying to run a GRU Text classification network. From a quick search on the web I saw some comments relating it to the pooling layers (i’m using globalmaxpooling1d and globalaveragepooling1d) but I’m really not sure.>

terminate called after throwing an instance of ‘dmlc::Error’ what(): [15:56:42] src/engine.threaded_engine.h:370: [15:56:42] src/operator/tensor/./matrix_op-inl.h:739: CropAssign only supports kWriteTo

A fatal error occurred in asynchronous engine operation. If you do not know what caused this error, you can try set environment variable MXNET_ENGINE_TYPE to NaiveEngine and run with debugger (i.e. gdb). This will force all operations to be synchronous and backtrace will give you the series of calls that lead to this error. Remember to set MXNET_ENGINE_TYPE back to empty after debugging.

Wonder if there’s something I’m doing wrong here.

Kind regards,
Theodore.

I got the same error. Please what do i do ?