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 vote346 views1 answer
Cookies in django
Python Django
0 vote307 views1 answer
Python missing characters hackerrank solution
Python
8 votes328 views6 answers
Python tutorial
Python
0 vote304 views1 answer
Drop row pandas column value not a number
Python
1 vote284 views1 answer
Change every value in a np array
Python
0 vote319 views3 answers
How to create a login page in python
Python
0 vote309 views1 answer
Python replace null in list
Python
1 vote306 views1 answer
Tkinter allign
Python
0 vote308 views1 answer
Python break out of function
Python
0 vote372 views2 answers
Flask upload file to s3
Python Flask