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 vote250 views4 answers
Client network socket disconnected before secure TLS connection was established
Python
0 vote273 views1 answer
Python size of linked list
Python
2 votes319 views1 answer
Django override delete
Python Django
14 votes276 views5 answers
Read excel sheet in python
Python
16 votes283 views5 answers
How to get only certain columns in pandas
Python
0 vote272 views1 answer
Python button graphics.py
Python
0 vote261 views1 answer
16 bit floating point numpy
Python
0 vote257 views10 answers
Python to c++ transpiler
Python
0 vote256 views1 answer
Convert json file to dict - if comming as list
Python
0 vote280 views1 answer
Is enumerate python lazy
Python