Gradient access (.grad) in PyTorch - Model Pipeline Trace

Model Pipeline - Gradient access (.grad)

This pipeline shows how a simple model learns by calculating gradients using PyTorch's .grad attribute. Gradients tell the model how to change its weights to improve predictions.

Data Flow - 5 Stages

1Data Input

4 rows x 2 columns→Provide input features and target labels→4 rows x 2 columns (features), 4 rows x 1 column (labels)

Features: [[1.0, 2.0], [2.0, 3.0], [3.0, 4.0], [4.0, 5.0]], Labels: [[3.0], [5.0], [7.0], [9.0]]

↓

2Model Initialization

2 features→Initialize weights and bias with requires_grad=True→Weights: 2 parameters, Bias: 1 parameter

Weights: tensor([0.5, -0.5], requires_grad=True), Bias: tensor(0.0, requires_grad=True)

↓

3Forward Pass

4 rows x 2 columns→Calculate predictions using linear model: y = Xw + b→4 rows x 1 column

Predictions: tensor([[0.5], [1.5], [2.5], [3.5]], requires_grad=True)

↓

4Loss Calculation

Predictions and labels (4 rows x 1 column each)→Compute mean squared error loss→Scalar loss value

Loss: tensor(10.25, requires_grad=True)

↓

5Backward Pass

Scalar loss→Calculate gradients of loss w.r.t weights and bias using .backward()→Gradients stored in .grad attributes of weights and bias

Weights.grad: tensor([-7.0, -10.0]), Bias.grad: tensor([-3.0])

Training Trace - Epoch by Epoch

Loss
10.25 |*       
 8.00 | *      
 6.00 |  *     
 4.00 |   *    
 2.56 |    *   
 1.00 |     *  
 0.64 |      * 
 0.16 |       *
 0.04 |        *
       ----------------
        1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	10.25	N/A	Initial loss is high; gradients calculated for first update
2	2.56	N/A	Loss decreased after weight update using gradients
3	0.64	N/A	Loss continues to decrease; gradients guide learning
4	0.16	N/A	Model is learning well; gradients become smaller
5	0.04	N/A	Loss is low; model predictions close to targets

Prediction Trace - 5 Layers

Layer 1: Input features

Layer 2: Linear layer calculation

Layer 3: Loss calculation

Layer 4: Backward pass (.backward())

Layer 5: Access .grad attribute

Model Quiz - 3 Questions

What does the .grad attribute store after calling backward()?

A The gradients of the loss with respect to the tensor

B The updated weights after training

C The input data to the model

D The final prediction values

Key Insight

The .grad attribute in PyTorch stores the gradients of the loss with respect to each parameter. These gradients guide how to update weights to reduce error. Accessing .grad after backward() is key to understanding and controlling learning.

Practice

1. What does the .grad attribute of a PyTorch tensor represent?

easy

A. The shape of the tensor

B. The value of the tensor itself

C. The gradient of the tensor after backpropagation

D. The data type of the tensor

Solution

1. Step 1: Understand the role of .grad in PyTorch

   The .grad attribute stores the gradient of the tensor computed during backpropagation.

2. Step 2: Differentiate from other tensor properties

   The tensor's value, shape, and data type are stored in other attributes, not .grad.

3. Final Answer:

   The gradient of the tensor after backpropagation -> Option C

4. Quick Check:

   .grad = gradient after backward() [OK]

Hint: Remember: .grad holds gradients after backward() [OK]

Common Mistakes:

• Confusing .grad with the tensor's value
• Expecting .grad before calling backward()
• Mixing .grad with tensor shape or dtype

2. Which of the following code snippets correctly accesses the gradient of a tensor x after backpropagation?

easy

A. grad = x.grad

B. grad = x.gradient()

C. grad = x.get_grad()

D. grad = x.gradient

Solution

1. Step 1: Recall the correct attribute for gradients

   PyTorch stores gradients in the .grad attribute, accessed as x.grad.

2. Step 2: Identify incorrect syntax

   Methods like gradient() or get_grad() do not exist for tensors.

3. Final Answer:

   grad = x.grad -> Option A

4. Quick Check:

   Use .grad attribute, not methods [OK]

Hint: Use .grad attribute, not functions [OK]

Common Mistakes:

• Trying to call .grad as a function
• Using incorrect method names
• Accessing .gradient instead of .grad

3. Consider the following PyTorch code:

import torch
x = torch.tensor(2.0, requires_grad=True)
y = x ** 3
z = y + 4
z.backward()
print(x.grad)

What will be the output of print(x.grad)?

medium

A. None

B. tensor(12.)

C. tensor(6.)

D. tensor(8.)

Solution

1. Step 1: Compute the derivative of z with respect to x

   Given y = x^3 and z = y + 4, the derivative is dz/dx = dy/dx = 3x^2.

2. Step 2: Calculate the gradient at x=2.0

   Plugging in x=2, 3 * (2)^2 = 3 * 4 = 12. So, x.grad will be tensor(12.).

3. Final Answer:

   tensor(12.) -> Option B

4. Quick Check:

   Derivative 3x^2 at x=2 = 12 [OK]

Hint: Calculate derivative manually, then plug in x [OK]

Common Mistakes:

• Forgetting to call backward() before accessing .grad
• Calculating derivative incorrectly
• Confusing y and z derivatives

4. You run this code:

import torch
x = torch.tensor(3.0, requires_grad=True)
y = x ** 2
print(x.grad)

But the output is None. Why?

medium

A. You forgot to call y.backward() to compute gradients

B. The tensor x does not require gradients

C. You cannot access gradients of scalar tensors

D. The tensor x is not a float

Solution

1. Step 1: Check if backward() was called

   Gradients are computed only after calling backward() on the output tensor.

2. Step 2: Confirm requires_grad=True and missing backward()

   Since x has requires_grad=True, the missing step is calling y.backward().

3. Final Answer:

   You forgot to call y.backward() to compute gradients -> Option A

4. Quick Check:

   Call backward() before accessing .grad [OK]

Hint: Always call backward() before checking .grad [OK]

Common Mistakes:

• Expecting .grad before backward()
• Confusing requires_grad flag
• Thinking .grad auto-updates without backward()

5. Given this code:

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=True)
y = (x ** 2).sum()
y.backward()
print(x.grad)

What will be the output of print(x.grad)?

hard

A. None

B. tensor([1., 2., 3.])

C. tensor([1., 4., 9.])

D. tensor([2., 4., 6.])

Solution

1. Step 1: Understand the function and gradient

   The function is y = sum(x_i^2). The gradient of y with respect to x_i is dy/dx_i = 2x_i.

2. Step 2: Calculate gradients for each element

   For x = [1, 2, 3], gradients are [2*1, 2*2, 2*3] = [2, 4, 6].

3. Final Answer:

   tensor([2., 4., 6.]) -> Option D

4. Quick Check:

   Gradient of x^2 is 2x element-wise [OK]

Hint: Gradient of x² is 2x for each element [OK]

Common Mistakes:

• Confusing sum of squares with squares of sums
• Forgetting element-wise gradient
• Expecting None without backward()