ValueError: array has incorrect number of dimensions: 3; expected 4

[xiexiaozheng]

When applying bias_correction to my model, an error occurs in the bias_correction.py script in the aimet. The error is located at line 340, specifically at "bias_correction.storePreActivationOutput(reference_output_batch)". The error message states: "ValueError: array has incorrect number of dimensions: 3; expected 4". The shape of reference_output_batch is (20, 256, 256), and the reference_layer is Conv1d(256, 256, kernel_size=(1,), stride=(1,)).

[quic-mangal]

@xiexiaozheng, we don't support Conv1d for bias correction ATM. If you would like, please try the Adaround technique instead of bias correction, it has proven to give much better results as compared to Bias correction.

[xiexiaozheng]

@xiexiaozheng, we don't support Conv1d for bias correction ATM. If you would like, please try the Adaround technique instead of bias correction, it has proven to give much better results as compared to Bias correction. I got it, thank you.