kernel_initializer="glorot_normal"

[puhan123]

In birealnet.py, I observe that kernel_initializer is set as "glorot_normal" for Conv2d; However, in QuantConv2D, the kernel_initializer is set as "glorot_normal".
Kernel_initializer ="glorot_normal" means the kernel weights are all set as 1 ?

Thank you very much.

[lgeiger]

Glorot normal draws samples from a truncated normal distribution centered on 0, so in this case it means binary weights will be randomly set to either -1 or 1.

[puhan123]

Thank you very much. I still have one more doubt.
Are both Conv2d and QuantConv2D all set to either -1 or 1?

[lgeiger]

Are both Conv2d and QuantConv2D all set to either -1 or 1?

Only weights of QuantConv2D layers will be binarized.

[puhan123]

My problem is that I found that the weights of QuantConv2D obtained with initialization method "glorot_normal" is not +1 or -1.
"glorot_normal" in Pytorch framework is as below:

The example is as :

The value of w is apparently not +1 or -1.
Thank you very much.