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 vote376 views1 answer
How to pass header in requests
Python
0 vote300 views1 answer
Exercism phone number python
Python
13 votes303 views3 answers
Python package version
Python
1 vote351 views2 answers
Convertir datetime to timestamp django
Python Django
0 vote292 views1 answer
Choose custom index pandas
Python
37 votes296 views1 answer
Python make txt file
Python
-1 vote296 views1 answer
What will be the output of the following python code? print("abc. def".capitalize())
Python
5 votes323 views1 answer
Tkinter maximum window size
Python
0 vote325 views1 answer
Python http request params
Python
0 vote310 views1 answer
How to remove text in pygame
Python