How are layer weights and biases initialized by default?

24

Hi @ptrblck !

Where in the programme should I add weights_init() function that you’ve defined ? Just after calling my model class ?
e.g
If I have a class Net() with my Network architecture, then In the main part I can do the following ?

model = Net() 
def weights_init(m):
    if isinstance(m, nn.Conv2d):
        xavier(m.weight.data)
        xavier(m.bias.data)

model.apply(weights_init)
optimizer=...
criterion=...

# Then the training Loop...

Is it a good way to initialize weight, then train my model ?

Thanks

1 Like