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 vote133 views1 answer
Python star sign before list
Python
0 vote127 views1 answer
Pytho ntoday as string
Python
0 vote142 views1 answer
Python add month datetime
Python
0 vote146 views1 answer
Pandas save dataframe with list
Python
0 vote142 views1 answer
Read the specific length of characters in a text file using the read() function
Python
0 vote131 views1 answer
Pandas head sort by colun name
Python
3 votes130 views1 answer
Python list of random float numbers
Python
4 votes127 views2 answers
Django queryset group by
Python
33 votes121 views5 answers
Float to int python
Python
4 votes139 views5 answers
Seaborn countplot
Python