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 vote152 views1 answer
Merge namedtuple python
Python
3 votes166 views1 answer
Datetimes to day of year python
Python
0 vote194 views1 answer
Created by and updated by in django
Python Django
0 vote180 views3 answers
Remove all parentheses from string python
Python
0 vote168 views1 answer
Python amino acid dictionary
Python
0 vote160 views1 answer
Can I convert python code to C++?
Python
0 vote174 views1 answer
List files in s3 folder python
Python
36 votes120 views10 answers
Python list keys from dictionary
Python
2 votes178 views1 answer
Add numpy array to pandas dataframe
Python
1 vote160 views3 answers
How to access variable of one function in another function in python
Python