Great works!
I read your code, but I am confused about the batch norm operation. I think batch norm in model prediction is (x-moving_mean)/movingvar * gamma + beta., while in the code is batchNorm[ + s] * val + batchNorm[ _ ]. I am not sure if it is correct.
Hello
The batch normalization equation was heavily modified for the model(Especially follow the way official Tensorflow Spleeter), which simplify computation.
Great works! I read your code, but I am confused about the batch norm operation. I think batch norm in model prediction is (x-moving_mean)/movingvar * gamma + beta., while in the code is batchNorm[ + s] * val + batchNorm[ _ ]. I am not sure if it is correct.