When encoder parameter "normalization" is set to None according documentation, training fails with the next error message:
TypeError: conv_bn_res_bn_actv() missing 2 required positional arguments: 'bn_momentum' and 'bn_epsilon'
The question is why it is using conv_bn_res_bn_actv() function, while "normalization" is set to None?
When encoder parameter "normalization" is set to None according documentation, training fails with the next error message:
TypeError: conv_bn_res_bn_actv() missing 2 required positional arguments: 'bn_momentum' and 'bn_epsilon'The question is why it is usingconv_bn_res_bn_actv()function, while "normalization" is set to None?