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 vote267 views3 answers
Python count
Python
4 votes203 views2 answers
Attributeerror: module 'tensorflow' has no attribute 'session'
Python
-1 vote310 views2 answers
Python datetime to string iso 8601
Python
0 vote275 views1 answer
List comprehension python one line
Python
1 vote288 views1 answer
Python requests set user agent
Python
2 votes264 views1 answer
Tkinter execute function on enter
Python
2 votes311 views3 answers
Python download for ubuntu 20.04
Python
44 votes273 views6 answers
Plt figsize
Python
5 votes329 views2 answers
My django template doesnt want to load the static file
Python Django
1 vote265 views1 answer
Piythin comment
Python