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 vote178 views1 answer
Np.arange and np.linspace difference
Python
1 vote257 views1 answer
Python game over screen
Python
2 votes189 views6 answers
Install nltk in python
Python
1 vote214 views1 answer
Python sympy solve equation equal to 0
Python
0 vote257 views1 answer
Iniciar servidor en Django
Python Django
0 vote254 views5 answers
Pattern
Python
1 vote253 views1 answer
Numpy
Python
0 vote191 views1 answer
Slice in iloc
Python
0 vote278 views3 answers
From unix timestamp to datetime pandas
Python
0 vote400 views2 answers
Axes color python
Python