‏Cross-Entropy للتصنيف متعدد الفئات

When your model must pick one label from many, like a digit 0 through 9, you use cross-entropy, the standard multiclass classification loss. 🔢

For C classes, your network outputs a vector of C raw scores called logits, one per possible class, for every sample in the batch.

Softmax exponentiates each logit and normalizes them so they sum to 1, turning raw scores into a clean probability distribution.

PyTorch bundles softmax and the loss into nn.CrossEntropyLoss. It scores how much probability your model put on the correct class.

This is the key rule: feed CrossEntropyLoss the raw logits, never a softmax output. It applies log-softmax internally for you.

Applying softmax yourself, then this loss, squashes the values twice. That double pass distorts gradients and quietly wrecks training.

Your targets are plain integer indices, like 3 for class three, not one-hot vectors. PyTorch handles the lookup for you.

Logits have shape batch by classes, while labels have shape batch only. A shape mismatch here is the most common cross-entropy error.

Under the hood, CrossEntropyLoss equals log-softmax followed by negative log-likelihood. Fusing them keeps the math numerically stable.

To get the final answer, take the argmax over the logits. The largest score is the predicted class, no softmax needed.

Setting label_smoothing nudges targets slightly away from a hard 1, which discourages overconfidence and often improves test accuracy.

You are using nn.CrossEntropyLoss for 10 classes. What should the model's final output be?

For multiclass tasks you feed raw logits and integer labels to CrossEntropyLoss, which softmaxes internally and scores the right class. Argmax gives the prediction. 🏆