Forward pass, loss, backward, step in PyTorch - Model Pipeline Trace

Model Pipeline - Forward pass, loss, backward, step

This pipeline shows how a simple neural network learns by passing data forward, calculating loss, going backward to find errors, and updating weights step-by-step.

Data Flow - 5 Stages

1Input Data

64 rows x 10 columns→Batch of 64 samples, each with 10 features→64 rows x 10 columns

[[0.5, 0.1, ..., 0.3], ..., [0.2, 0.4, ..., 0.7]]

↓

2Forward Pass

64 rows x 10 columns→Data passed through linear layer and activation→64 rows x 3 columns

[[1.2, 0.5, -0.3], ..., [0.7, 1.1, 0.0]]

↓

3Loss Calculation

64 rows x 3 columns (predictions), 64 rows (labels)→Calculate cross-entropy loss between predictions and true labels→Scalar loss value

Loss = 1.23

↓

4Backward Pass

Scalar loss value→Compute gradients of loss w.r.t model weights→Gradients stored in model parameters

Gradients like weight.grad = [[0.01, -0.02, ...], ...]

↓

5Optimizer Step

Model parameters with gradients→Update model weights using gradients and learning rate→Updated model parameters

Weights changed from 0.5 to 0.48

Training Trace - Epoch by Epoch

Loss
1.3 |*       
1.1 | *      
0.9 |  *     
0.7 |   *    
0.5 |    *   
    +---------
     1 2 3 4 5
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.23	0.45	Loss starts high, accuracy low as model begins learning
2	0.95	0.60	Loss decreases, accuracy improves
3	0.75	0.70	Model continues to learn, better predictions
4	0.60	0.78	Loss steadily decreases, accuracy rises
5	0.50	0.82	Training converging, model improving

Prediction Trace - 7 Layers

Layer 1: Input Layer

Layer 2: Linear Layer

Layer 3: Activation (ReLU)

Layer 4: Softmax

Layer 5: Loss Calculation

Layer 6: Backward Pass

Layer 7: Optimizer Step

Model Quiz - 3 Questions

What happens during the backward pass?

A Calculate gradients of loss with respect to weights

B Update weights using gradients

C Pass input data through the model

D Calculate the loss value

Key Insight

This visualization shows how a model learns step-by-step: it passes data forward to predict, measures error with loss, goes backward to find how to improve, and updates weights to get better over time.

Practice

1. What is the main purpose of the forward pass in a PyTorch model?

easy

A. To compute gradients for backpropagation

B. To update the model weights after training

C. To run input data through the model and get predictions

D. To calculate the loss between predictions and targets

Solution

1. Step 1: Understand the forward pass role

   The forward pass takes input data and processes it through the model layers to produce predictions.

2. Step 2: Differentiate from other steps

   Updating weights is done by the optimizer step, loss calculation measures error, and backward computes gradients.

3. Final Answer:

   To run input data through the model and get predictions -> Option C

4. Quick Check:

   Forward pass = predictions [OK]

Hint: Forward pass means getting predictions from inputs [OK]

Common Mistakes:

• Confusing forward pass with weight update
• Mixing loss calculation with forward pass
• Thinking backward computes predictions

2. Which of the following is the correct PyTorch code to perform a backward pass on a loss tensor named loss?

easy

A. loss.step()

B. loss.backward()

C. loss.forward()

D. loss.update()

Solution

1. Step 1: Identify the backward method

   In PyTorch, calling loss.backward() computes gradients for all tensors with requires_grad=True.

2. Step 2: Check other options

   step() is for optimizers, forward() is for models, and update() is not a PyTorch method.

3. Final Answer:

   loss.backward() -> Option B

4. Quick Check:

   Backward pass uses loss.backward() [OK]

Hint: Use loss.backward() to compute gradients [OK]

Common Mistakes:

• Using step() on loss instead of optimizer
• Calling forward() on loss tensor
• Trying to update loss directly

3. Given the following PyTorch code snippet, what will be printed?

import torch
import torch.nn as nn

model = nn.Linear(2, 1)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

inputs = torch.tensor([[1.0, 2.0]])
targets = torch.tensor([[1.0]])

outputs = model(inputs)
loss_fn = nn.MSELoss()
loss = loss_fn(outputs, targets)

loss.backward()
optimizer.step()

print(loss.item())

medium

A. A positive float value representing the loss before weight update

B. Zero, because optimizer.step() resets the loss

C. A tensor object, not a float

D. An error because backward() must be called after step()

Solution

1. Step 1: Understand loss calculation and printing

   The loss is computed before backward and step, so loss.item() returns the scalar loss value as a float.

2. Step 2: Confirm optimizer.step() effect

   Calling optimizer.step() updates weights but does not change the already computed loss tensor value.

3. Final Answer:

   A positive float value representing the loss before weight update -> Option A

4. Quick Check:

   loss.item() shows loss before update [OK]

Hint: Loss printed is before optimizer updates weights [OK]

Common Mistakes:

• Thinking loss becomes zero after optimizer.step()
• Expecting loss to be a tensor when printed
• Calling backward() after step() causes error

4. Identify the error in this PyTorch training snippet:

optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
outputs = model(inputs)
loss = loss_fn(outputs, targets)
optimizer.step()
loss.backward()

medium

A. Missing optimizer.zero_grad() before backward

B. Model parameters not passed to optimizer

C. Using wrong loss function

D. Calling optimizer.step() before loss.backward()

Solution

1. Step 1: Check order of backward and step

   Gradients must be computed by loss.backward() before calling optimizer.step() to update weights.

2. Step 2: Analyze given code order

   The code calls optimizer.step() before loss.backward(), so weights update happens without gradients.

3. Final Answer:

   Calling optimizer.step() before loss.backward() -> Option D

4. Quick Check:

   Backward before step is required [OK]

Hint: Always call loss.backward() before optimizer.step() [OK]

Common Mistakes:

• Swapping backward and step order
• Forgetting to zero gradients
• Assuming step() computes gradients

5. You want to train a PyTorch model for one step with input x and target y. Which sequence of commands correctly performs forward pass, loss calculation, backward pass, and weight update?

hard

A. optimizer.zero_grad(); outputs = model(x); loss = loss_fn(outputs, y); loss.backward(); optimizer.step()

B. outputs = model(x); loss = loss_fn(outputs, y); optimizer.step(); loss.backward(); optimizer.zero_grad()

C. loss = loss_fn(x, y); outputs = model(x); optimizer.zero_grad(); loss.backward(); optimizer.step()

D. optimizer.step(); optimizer.zero_grad(); outputs = model(x); loss = loss_fn(outputs, y); loss.backward()

Solution

1. Step 1: Understand correct training step order

   The correct order is: clear gradients, forward pass, compute loss, backward pass, then update weights.

2. Step 2: Check each option's sequence

   optimizer.zero_grad(); outputs = model(x); loss = loss_fn(outputs, y); loss.backward(); optimizer.step() follows the correct order. Others call optimizer.step() too early or compute loss before forward pass.

3. Final Answer:

   optimizer.zero_grad(); outputs = model(x); loss = loss_fn(outputs, y); loss.backward(); optimizer.step() -> Option A

4. Quick Check:

   Zero grad -> forward -> loss -> backward -> step [OK]

Hint: Clear grads, forward, loss, backward, then step [OK]

Common Mistakes:

• Calling optimizer.step() before backward
• Not zeroing gradients before backward
• Computing loss before forward pass