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

51 votes267 views6 answers
Python logging to file
Python
0 vote221 views1 answer
Python continue inner for loop
Python
0 vote240 views1 answer
Python type hints list of class
Python
43 votes249 views6 answers
Python array to string
Python
-1 vote235 views5 answers
Sudo apt install python3-pip
Python
2 votes258 views5 answers
Table in python
Python
0 vote277 views1 answer
How to initialize pygame
Python
0 vote254 views1 answer
Pprint dic without sorting
Python
0 vote265 views1 answer
Doormat pattern
Python
0 vote240 views1 answer
Where to import kivy builder
Python