all concat input tensors must have the same dimensions except on the concatenation axis

I have two errors as follow in converting to TensorRT engine.

[TensorRT] ERROR: concat_stage2: all concat input tensors must have the same dimensions except on the concatenation axis
[TensorRT] ERROR: UffParser: Parser error: Mconv1_stage2_L1/BiasAdd: The input to the Scale Layer is required to have a minimum of 3 dimensions.

I have all input tensors in same dimensions for concat_stage2. Please see in image.
https://www.dropbox.com/s/6m8lgn3w14e26bj/1.png?dl=0

Then for Mconv1_stage2_L1/BiasAdd, what does it mean for this error?
The image is attached for the Mconv1_stage2_L1/BiasAdd.

https://www.dropbox.com/s/3dahu3sk3s08ijl/2.png?dl=0

How to solve the error?