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 vote106 views2 answers
How to install modules to a specific version of python
Python
11 votes107 views3 answers
Get yesterday date python
Python
0 vote113 views1 answer
Python add hyphen to string
Python
2 votes138 views2 answers
What is role of ALLOWED_HOSTs in Django
Python Django
1 vote118 views1 answer
Choose random file from directory
Python
2 votes110 views2 answers
Python convert hex to binary
Python
0 vote143 views2 answers
Install socketio flask
Python Flask
0 vote109 views1 answer
Modulenotfounderror no module named 'config' python
Python
68 votes117 views6 answers
Python clear console
Python
0 vote116 views3 answers
OpenCV(3.4.11) Error: Assertion failed (_img.rows * _img.cols == vecSize) in CvCascadeImageReader::PosReader::get
Python