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 vote324 views1 answer
Which type of programming does python support?
Python
10 votes348 views4 answers
Takes 1 positional argument but 2 were given python
Python
2 votes306 views3 answers
Can't find model 'en_core_web_sm'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.
Python
0 vote305 views1 answer
Run all python files in a directory in windows
Python
32 votes312 views1 answer
How to add a column to a pandas df
Python
3 votes319 views1 answer
How to create a label in tkinter python
Python
37 votes313 views5 answers
Run python file from cmd
Python
8 votes324 views3 answers
Calculate euclidian distance python
Python
0 vote367 views1 answer
Lineplot in plt
Python
0 vote318 views1 answer
Not staments python
Python