pytorch get weights

Flyhouse_Squarewheel answered on October 30, 2024 Popularity 1/10 Helpfulness 1/10

answer pytorch get weights

pytorch get weights

Comment

2 ways I know depends on initialization. Note, gets weights as a torch.Tensor

class My_Model_1(nn.Module):
    def __init__(self,D_in,D_out):
        super(My_Model_1, self).__init__()
        self.layer = nn.Linear(D_in,D_out)
    def forward(self,x):
        out = self.layer(x)
        return out

class My_Model_2(nn.Module):
    def __init__(self,D_in,D_out):
        super(My_Model_2, self).__init__()
        self.layer = nn.Sequential(nn.Linear(D_in,D_out))
    def forward(self,x):
        out = self.layer(x)
        return out

model_1 = My_Model_1(10,10)
print(model_1.layer.weight)
model_2 = My_Model_2(10,10)
print(model_2.layer[0].weight)

https://discuss.pytorch.org/t/access-weights-of-a-specific-module-in-nn-sequential/3627

Popularity 1/10 Helpfulness 1/10 Language python

Source: Grepper

Tags: get python pytorch

Link to this answer
Share Copy Link