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

0 vote115 views1 answer
Formula e xiaomi
Python
0 vote110 views1 answer
Python double underscore methods
Python
2 votes110 views2 answers
Months list python
Python
1 vote99 views1 answer
Get int value of char python
Python
1 vote110 views1 answer
Selenium close current driver but don't quit
Python
0 vote105 views1 answer
Bad request 400 heroku app
Python
0 vote72 views1 answer
Node alpine install python
Python
0 vote172 views1 answer
Def batting(balls,runs): points=runs/2; if runs>50: points=points+5; if runs>=100: points=points+10; strikerate=runs/balls; if strikerate>=80 and strikerate<=100: points=points+2; elif strikerate>100: points=points+4; print(points)
Python
4 votes100 views1 answer
How to add column headers in pandas
Python
2 votes107 views3 answers
Python format currency
Python