Forward pass, loss, backward, step in PyTorch

Introduction

We use these steps to teach a computer how to learn from data by guessing, checking mistakes, and improving.

When training a model to recognize images like cats and dogs.

When teaching a robot to understand spoken commands.

When building a system to predict house prices from features.

When improving a chatbot to give better answers.

When adjusting a model to classify emails as spam or not.

Syntax

PyTorch

output = model(input)
loss = loss_function(output, target)
loss.backward()
optimizer.step()
optimizer.zero_grad()

output = model(input) runs the data through the model to get predictions.

loss.backward() calculates how to change the model to reduce mistakes.

Examples

Basic training step with input x and target y.

PyTorch

output = model(x)
loss = criterion(output, y)
loss.backward()
optimizer.step()
optimizer.zero_grad()

Training step for image data with predictions and labels.

PyTorch

predictions = model(images)
loss = loss_fn(predictions, labels)
loss.backward()
optimizer.step()
optimizer.zero_grad()

Sample Model

This code creates a simple model that learns to predict targets from inputs. It shows the loss before and after one training step.

PyTorch

import torch
import torch.nn as nn
import torch.optim as optim

# Simple model: one linear layer
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(2, 1)
    def forward(self, x):
        return self.linear(x)

# Data: inputs and targets
inputs = torch.tensor([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])
targets = torch.tensor([[3.0], [7.0], [11.0]])

# Model, loss, optimizer
model = SimpleModel()
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Training step
output = model(inputs)
loss = criterion(output, targets)
print(f"Loss before backward: {loss.item():.4f}")

loss.backward()
optimizer.step()
optimizer.zero_grad()

# Check loss after one step
output2 = model(inputs)
loss2 = criterion(output2, targets)
print(f"Loss after one step: {loss2.item():.4f}")

Important Notes

Always call optimizer.zero_grad() before loss.backward() to clear old gradients.

The loss.backward() step calculates gradients automatically for all model parameters.

The optimizer.step() updates the model weights using the gradients.

Summary

The forward pass runs data through the model to get predictions.

The loss measures how far predictions are from targets.

Backward computes gradients to know how to improve the model.

Step updates the model weights to reduce future mistakes.

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