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 vote265 views1 answer
Pandas dataframe unique multiple columns
Python
1 vote285 views1 answer
Ros beginner tutorial python publisher
Python
0 vote315 views1 answer
What if discord.py python add-in does not work
Python
1 vote283 views1 answer
How to find second maximum element of an array python
Python
28 votes249 views7 answers
Anagram python
Python
2 votes294 views1 answer
Max of matrix numpy
Python
22 votes273 views6 answers
Add python to path
Python
12 votes302 views2 answers
Read excel file spyder
Python
13 votes279 views6 answers
Range in python
Python
-1 vote318 views1 answer
Add widget in pyqt
Python