Hailo optimization/calibration on Yolox produces error

The error looks like this:

NegativeSlopeExponentNonFixable(output_bits=output_bits, fix_shift=fix_shift, lname=layer.name)
hailo_model_optimization.acceleras.utils.acceleras_exceptions.NegativeSlopeExponentNonFixable: Quantization failed in layer model/convXX due to unsupported required slope. Desired shift is 12.0, but op has only 8 data bits. This error raises when the data or weight range are not balanced. Mostly happens when using random calibration-set/weights, the calibration-set is not normalized properly or batch-normalization was not used during training.

If it is yolox, make sure you don’t normalize the data. Yolox, contrary to other model, is usually trained with data in the [0, 255] range. Therefore, the input doesn’t need to be normalized to [0, 1].