ERROR: 02_pytorch_classification --> error in 8.5 Training and Testing for multi-class Pytorch model

[fivefishstudios]

In section 8.5, (multi-class classification model), this section produces an error message

`# Fit the model
torch.manual_seed(42)

Set number of epochs

epochs = 100

Put data to target device

X_blob_train, y_blob_train = X_blob_train.to(device), y_blob_train.to(device)
X_blob_test, y_blob_test = X_blob_test.to(device), y_blob_test.to(device)

for epoch in range(epochs):
### Training
model_4.train()

# 1. Forward pass
y_logits = model_4(X_blob_train) # model outputs raw logits 
y_pred = torch.softmax(y_logits, dim=1).argmax(dim=1) # go from logits -> prediction probabilities -> prediction labels

# 2. Calculate loss and accuracy
loss = loss_fn(y_pred, y_blob_train) 
acc = accuracy_fn(y_true=y_blob_train,
                  y_pred=y_pred)

# 3. Optimizer zero grad
optimizer.zero_grad()

# 4. Loss backwards
loss.backward()

# 5. Optimizer step
optimizer.step()

### Testing
model_4.eval()
with torch.inference_mode():
  # 1. Forward pass
  test_logits = model_4(X_blob_test)
  test_pred = torch.softmax(test_logits, dim=1).argmax(dim=1)
  # 2. Calculate test loss and accuracy
  test_loss = loss_fn(test_logits, y_blob_test)
  test_acc = accuracy_fn(y_true=y_blob_test,
                         y_pred=test_pred)

# Print out what's happening
if epoch % 10 == 0:
    print(f"Epoch: {epoch} | Loss: {loss:.5f}, Acc: {acc:.2f}% | Test Loss: {test_loss:.5f}, Test Acc: {test_acc:.2f}%") 

`

The error is: Expected floating point type for target with class probabilities, got Long

I'm on OSX, Pytorch '1.12.1'

---

RuntimeError Traceback (most recent call last)
in
18
19 # 2. Calculate loss and accuracy
---> 20 loss = loss_fn(y_pred, y_blob_train)
21 acc = accuracy_fn(y_true=y_blob_train,
22 y_pred=y_pred)

~/opt/anaconda3/envs/MachineLearning/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1128 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1129 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1130 return forward_call(*input, **kwargs)
1131 # Do not call functions when jit is used
1132 full_backward_hooks, non_full_backward_hooks = [], []

~/opt/anaconda3/envs/MachineLearning/lib/python3.8/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
1162
1163 def forward(self, input: Tensor, target: Tensor) -> Tensor:
-> 1164 return F.cross_entropy(input, target, weight=self.weight,
1165 ignore_index=self.ignore_index, reduction=self.reduction,
1166 label_smoothing=self.label_smoothing)

~/opt/anaconda3/envs/MachineLearning/lib/python3.8/site-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
3012 if size_average is not None or reduce is not None:
3013 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 3014 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
3015
3016

RuntimeError: Expected floating point type for target with class probabilities, got Long

[tonyhaya]

The loss don't receive y_pred, instead use y_logit

[Arsive02]

"""The combination of nn.LogSoftmax and nn.NLLLoss is equivalent to using nn.CrossEntropyLoss. This terminology is a particularity of PyTorch, as the nn.NLLoss [sic] computes, in fact, the cross entropy but with log probability predictions as inputs where nn.CrossEntropyLoss takes scores (sometimes called logits). Technically, nn.NLLLoss is the cross entropy between the Dirac distribution, putting all mass on the target, and the predicted distribution given by the log probability inputs."""
Reason

[tonyhaya]

loss = loss_fn(y_logits, y_blob_train)
acc = accuracy_fn(y_true=y_blob_train, y_pred=y_pred)

[mrdbourke]

Thank you for helping!