Closed jicampos closed 1 year ago
We are adding bias in QuantConv2d and QuantBnConv2d when exporting to the QONNX format. Batchnorm. folding with QuantBnConv2d is now included as well. If flag _fixBN is not set, exporting will include the Batchnorm layer.
We are adding bias in QuantConv2d and QuantBnConv2d when exporting to the QONNX format. Batchnorm. folding with QuantBnConv2d is now included as well. If flag _fixBN is not set, exporting will include the Batchnorm layer.