Why the loss function is always printing zero after the first epoch?
I suspect it’s because of loss = loss_fn(outputs, torch.max(labels, 1)[1])
.
And if if I use loss = loss_fn(outputs, torch.max(labels, 1)[0])
, I will get some values that are too high and I’m not sure if they make sense, like: 1200,800,600,500(one value for each epoc)
nepochs = 5
losses = np.zeros(nepochs)
loss_fn = nn.CrossEntropyLoss()
optimizer = optim.Adam(modell.parameters(), lr = 0.001)
for epoch in range(nepochs):
running_loss = 0.0
n = 0
for data in train_loader:
#single batch
if(n == 1):
break;
inputs, labels = data
optimizer.zero_grad()
outputs = modell(inputs)
#loss = loss_fn(outputs, labels)
loss = loss_fn(outputs, torch.max(labels, 1)[1])
loss.backward()
optimizer.step()
running_loss += loss.item()
n += 1
losses[epoch] = running_loss / n
print(f"epoch: {epoch+1} loss: {losses[epoch] : .3f}")
The model is:
def __init__(self, labels=10):
super(Classifier, self).__init__()
self.fc = nn.Linear(3 * 64 * 64, labels)
def forward(self, x):
out = x.reshape(x.size(0), -1)
out = self.fc (out)
return out
the labels
variable is a 64 tensor size like this
tensor([[7],[1],[ 2],[3],[ 2],[9],[9],[8],[9],[8],[ 1],[7],[9],[2],[ 5],[1],[3],[3],[8],[3],[7],[1],[7],[9],[8],[ 8],[3],[7],[ 5],[ 1],[7],[3],[2],[1],[ 3],[3],[2],[0],[3],[4],[0],[7],[1],[ 8],[4],[1],[ 5],[ 3],[4],[3],[ 4],[8],[4],[1],[ 9],[7],[3],[ 2],[ 6],[4],[ 8],[3],[ 7],[3]])