Hello, I've learned a lot from Neurosim,
But I have a quick question about network architecture:
I didn't see batchnormalization code in any part of code related to network structure definitions, such as modules/ quantization_cpu_np_infer. py and cifar /model.py, Is there no Batchnormalization layer? And why not?
thanks!
Hi! The batch normalization is replaced by constant scaling in the "WAGE" algorithm with integers training. You can check the paper https://arxiv.org/pdf/1802.04680.pdf for more details.
Hello, I've learned a lot from Neurosim, But I have a quick question about network architecture: I didn't see batchnormalization code in any part of code related to network structure definitions, such as modules/ quantization_cpu_np_infer. py and cifar /model.py, Is there no Batchnormalization layer? And why not? thanks!