Loss functions (MSELoss, CrossEntropyLoss) in PyTorch - Model Pipeline Trace

Model Pipeline - Loss functions (MSELoss, CrossEntropyLoss)

This pipeline shows how two common loss functions, MSELoss and CrossEntropyLoss, help a model learn by measuring errors during training. MSELoss is used for predicting numbers, while CrossEntropyLoss is for classifying categories.

Data Flow - 5 Stages

1Input Data

1000 rows x 10 features→Raw data with 10 features per example→1000 rows x 10 features

[[0.5, 1.2, ..., 0.3], [0.1, 0.4, ..., 0.9], ...]

↓

2Model Prediction (Regression)

1000 rows x 10 features→Model outputs continuous values (1 per example)→1000 rows x 1 value

[[2.3], [0.7], [1.5], ...]

↓

3Model Prediction (Classification)

1000 rows x 10 features→Model outputs raw scores (logits) for 3 classes→1000 rows x 3 classes

[[1.2, 0.5, -0.3], [0.1, 2.0, 1.1], ...]

↓

4Loss Calculation (MSELoss)

Predictions: 1000 rows x 1, Targets: 1000 rows x 1→Calculate mean squared error between predicted and true values→Single scalar loss value

Loss = 0.045

↓

5Loss Calculation (CrossEntropyLoss)

Predictions: 1000 rows x 3, Targets: 1000 rows (class labels)→Calculate cross-entropy loss between predicted logits and true class labels→Single scalar loss value

Loss = 0.67

Training Trace - Epoch by Epoch

Loss
1.0 |*       
0.8 | **     
0.6 |  ***   
0.4 |    *** 
0.2 |      **
0.0 +--------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.45	High loss and low accuracy at start
2	0.60	0.62	Loss decreased, accuracy improved
3	0.42	0.75	Model learning well, loss dropping
4	0.30	0.82	Loss continues to decrease, accuracy rising
5	0.22	0.88	Good convergence, model improving

Prediction Trace - 3 Layers

Layer 1: Input Features

Layer 2: Model Forward Pass

Layer 3: CrossEntropyLoss Calculation

Model Quiz - 3 Questions

Which loss function is best for predicting continuous numbers?

A CrossEntropyLoss

B Hinge Loss

C MSELoss

D Binary Cross Entropy

Key Insight

Loss functions like MSELoss and CrossEntropyLoss guide the model to improve by measuring how far predictions are from true answers. Watching loss decrease during training shows the model is learning well.

Practice

1. Which loss function in PyTorch is best suited for predicting continuous values like house prices?

easy

A. torch.nn.MSELoss

B. torch.nn.CrossEntropyLoss

C. torch.nn.BCELoss

D. torch.nn.NLLLoss

Solution

1. Step 1: Understand the type of prediction

   Predicting house prices is a regression problem where output is continuous.

2. Step 2: Match loss function to problem type

   MSELoss calculates mean squared error, ideal for continuous outputs. CrossEntropyLoss is for classification, not regression.

3. Final Answer:

   torch.nn.MSELoss -> Option A

4. Quick Check:

   Regression uses MSELoss = C [OK]

Hint: Use MSELoss for continuous outputs, CrossEntropyLoss for classes [OK]

Common Mistakes:

• Choosing CrossEntropyLoss for regression tasks
• Confusing BCELoss with MSELoss
• Using NLLLoss without log probabilities

2. Which of the following is the correct way to create a CrossEntropyLoss object in PyTorch?

easy

A. loss = torch.nn.CrossEntropy()

B. loss = torch.nn.MSELoss()

C. loss = torch.nn.CrossEntropyLoss()

D. loss = torch.CrossEntropyLoss()

Solution

1. Step 1: Recall PyTorch loss function syntax

   Loss functions are in torch.nn and instantiated with parentheses.

2. Step 2: Identify correct class name and module

   CrossEntropyLoss is the correct class name under torch.nn. Options A misses 'Loss' and C misses 'nn'.

3. Final Answer:

   loss = torch.nn.CrossEntropyLoss() -> Option C

4. Quick Check:

   Correct class and module = D [OK]

Hint: Use torch.nn.CrossEntropyLoss() exactly for classification loss [OK]

Common Mistakes:

• Missing parentheses when creating loss object
• Using torch.CrossEntropyLoss() instead of torch.nn.CrossEntropyLoss()
• Confusing MSELoss with CrossEntropyLoss

3. What will be the output loss value when using torch.nn.MSELoss on predictions tensor([2.0, 3.0]) and targets tensor([1.0, 5.0])?

medium

A. 2.5

B. 3.0

C. 1.5

D. 4.0

Solution

1. Step 1: Calculate squared differences

   Differences: (2.0-1.0)=1.0, (3.0-5.0)=-2.0; squared: 1.0, 4.0

2. Step 2: Compute mean of squared differences

   Mean = (1.0 + 4.0) / 2 = 2.5

3. Final Answer:

   2.5 -> Option A

4. Quick Check:

   MSE = mean squared error = 2.5 [OK]

Hint: Square errors, then average for MSELoss output [OK]

Common Mistakes:

• Forgetting to square the differences
• Summing without averaging
• Mixing up prediction and target order

4. Given this code snippet, what is the error?

import torch
loss_fn = torch.nn.CrossEntropyLoss()
pred = torch.tensor([[0.2, 0.8], [0.6, 0.4]])
target = torch.tensor([1, 0])
loss = loss_fn(pred, target)
print(loss.item())

medium

A. Loss function should be MSELoss for this target

B. Target tensor should be one-hot encoded

C. No error, code runs correctly

D. Predictions should be raw scores (logits), not probabilities

Solution

1. Step 1: Check input requirements for CrossEntropyLoss

   CrossEntropyLoss expects raw scores (logits), not probabilities.

2. Step 2: Analyze given predictions

   Predictions are probabilities (sum to 1), so applying CrossEntropyLoss directly causes incorrect loss calculation.

3. Final Answer:

   Predictions should be raw scores (logits), not probabilities -> Option D

4. Quick Check:

   CrossEntropyLoss needs logits = A [OK]

Hint: Use logits, not probabilities, with CrossEntropyLoss [OK]

Common Mistakes:

• Passing probabilities instead of logits to CrossEntropyLoss
• Using one-hot targets instead of class indices
• Confusing MSELoss with CrossEntropyLoss for classification

5. You have a multi-class classification problem with 4 classes. Your model outputs raw scores (logits) of shape (batch_size, 4). Which loss function and target format should you use in PyTorch?

hard

A. Use torch.nn.MSELoss with target as one-hot vectors

B. Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3)

C. Use torch.nn.BCELoss with target as class indices

D. Use torch.nn.CrossEntropyLoss with target as one-hot vectors

Solution

1. Step 1: Identify loss function for multi-class classification

   CrossEntropyLoss is designed for multi-class classification with logits.

2. Step 2: Determine correct target format

   CrossEntropyLoss expects target as class indices (integers), not one-hot vectors.

3. Final Answer:

   Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3) -> Option B

4. Quick Check:

   CrossEntropyLoss + class indices = B [OK]

Hint: CrossEntropyLoss needs logits and integer class labels [OK]

Common Mistakes:

• Passing one-hot vectors as targets to CrossEntropyLoss
• Using MSELoss for classification
• Using BCELoss for multi-class without sigmoid