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 vote276 views3 answers
Making ckeditor django responsive
Python
0 vote272 views1 answer
How to use drf permission class with class method actions
Python
0 vote312 views2 answers
Python file is writable
Python
1 vote275 views2 answers
Python return using if
Python
0 vote269 views1 answer
Testing logging python
Python
0 vote285 views1 answer
Python - join two columns and transform it as index
Python
0 vote296 views2 answers
String validators hackerrank solution
Python
3 votes262 views2 answers
Python file location path
Python
2 votes294 views1 answer
Python RuntimeWarning: overflow encountered in long_scalars
Python
1 vote263 views2 answers
How to find the shortest word in a list python
Python