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