CNN weights initialization

vision
1

How I could initialize fixed weights for cnn each time when I start training?

2

Hi,

You want every initialization of your network to be the same when you start training?
You can set random seeds for that.
Be careful though that many things are non-deterministic and so won’t behave exactly the same between runs. You can read more about this here.

1 Like
3

I want to compare performance between 3 CNNs but I want to fix the weights to ensure that the changes in performance doesn’t comes from weights random initialization of each

4

Hi,
The thing is that the random value of the weights might favor one architecture/training procedure over the others. So fixing one random initialization is not really a fair comparison.
To prevent weight initialization from interfering, you would need to run each model to a few random seeds and compare average and variance of their performances.

1 Like