Code QuizIntermediate

Feedforward Network Output Layer

Spot the extra activation applied to the output layer.

Codepython
import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 10)
    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        return x

What is the bug in this classification network?

Watch the code walkthrough

Watch on YouTube →