Batchnorm1d pytorch

class network(nn.Module):
    def __init__(self):
        super(network, self).__init__()
        self.linear1 = nn.Linear(in_features=40, out_features=320)
        self.bn1 = nn.BatchNorm1d(num_features=320)
        self.linear2 = nn.Linear(in_features=320, out_features=2)

    def forward(self, input):  # Input is a 1D tensor
        y = F.relu(self.bn1(self.linear1(input)))
        y = F.softmax(self.linear2(y), dim=1)
        return y
    
model = network()
x = torch.randn(10, 40)
output = model(x)

Source: discuss.pytorch.org

Similar codes

1 vote322 views1 answer
Ipykernel pip
Python
25 votes339 views6 answers
Python online compiler
Python
0 vote309 views1 answer
Send command dynamo civid
Python
0 vote320 views1 answer
Drop rows with null date in pandas
Python
14 votes315 views2 answers
How to change the background of heading in tkinter
Python
0 vote310 views1 answer
Dictionary input from user in python3
Python
0 vote382 views1 answer
Intersection python dict
Python
61 votes340 views6 answers
Remove from string python
Python
4 votes367 views1 answer
What is cleaned data in django
Python Django
3 votes334 views1 answer
Pandas merge all csv in a folder
Python