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 vote188 views1 answer
How to create empty series in pandas
Python
14 votes204 views4 answers
Python lambda function if else
Python
2 votes199 views2 answers
Background image in python
Python
0 vote193 views1 answer
Python valueerror "invalid syntax for number"
Python
1 vote196 views1 answer
Keras.layers.simplernn
Python
2 votes196 views3 answers
Cosine interpolation
Python
3 votes220 views1 answer
Flask delete cookie stackoverflow
Python Flask
0 vote179 views2 answers
Render template in django
Python
0 vote201 views1 answer
Tkinter start maximized
Python
0 vote188 views1 answer
Selenium save webpage as pdf python
Python