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

9 votes146 views4 answers
Display full dataframe pandas
Python
0 vote144 views1 answer
Procfile heroku python example
Python
3 votes184 views2 answers
Python save a dictionary as an object
Python
131 votes149 views6 answers
How to generate random numbers in python
Python
1 vote184 views1 answer
Plt.plot width line
Python
30 votes294 views6 answers
How to create a superuser in django
Python Django
0 vote226 views1 answer
How to make a python script write the minimum and maximum value
Python
2 votes213 views2 answers
Django queryset is in list
Python Django
4 votes158 views1 answer
Concat dataframe from list of dataframe
Python
0 vote182 views1 answer
Concat dataset
Python