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

2 votes273 views2 answers
Python how to sum two lists
Python
2 votes249 views2 answers
Python check string for negative number
Python
0 vote249 views1 answer
Pygame mixer channel loop
Python
0 vote256 views2 answers
Doormat pattern python
Python
8 votes284 views2 answers
Django create empty migration
Python Django
0 vote275 views2 answers
Print out python
Python
0 vote261 views1 answer
How to make a label in python
Python
0 vote244 views1 answer
Map dataframe parallel
Python
114 votes274 views6 answers
Amc price
Python
0 vote243 views2 answers
Popups in tkinter
Python