[Tensorflow][Relay] relay.concatenate requires all tensors have the same ndim;


#1

Hi,

I have a model with a concat operator in TF. It has a concatenate operator in which apparently one of the input tensor has a different shape. Then I got the error relay.concatenate requires all tensors have the same ndim;. Is this a limitation of TVM?, What are possible solutions for this issue?

Thanks


[Relay][Concatenate] Can not concatenate outputs of conv2d with different number of channels
#2

@tico did you ever resolve this?


#3

I resolved it by removing the offending concat operator from my model and implementing that part of the model in an alternative way. After checking the model with the concat operator I was not able to identify anything wrong with that operator.