Augmentation policy search (AutoAugment) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the AutoAugment policy from torchvision.

Computer Vision

from torchvision.transforms import [1]

Drag options to blanks, or click blank then click option'

ANormalize

BAutoAugment

CRandomCrop

DToTensor

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated transforms like RandomCrop or Normalize instead of AutoAugment.

The AutoAugment class is imported from torchvision.transforms to apply augmentation policies automatically.

2fill in blank

medium

Complete the code to create an AutoAugment transform with the CIFAR10 policy.

Computer Vision

transform = AutoAugment(policy=[1])

Drag options to blanks, or click blank then click option'

AAutoAugmentPolicy.CIFAR10

BAutoAugmentPolicy.IMAGENET

CAutoAugmentPolicy.SVHN

DAutoAugmentPolicy.MNIST

Attempts:

3 left

💡 Hint

Common Mistakes

Using the ImageNet or SVHN policies which are not suitable for CIFAR10 images.

The CIFAR10 policy is used here to apply augmentation suitable for CIFAR10 images.

3fill in blank

hard

Fix the error in applying AutoAugment transform to the dataset.

Computer Vision

dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=[1])

Drag options to blanks, or click blank then click option'

AAutoAugment()

Btransform()

CAutoAugment

Dtransform

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the class name without parentheses, causing a type error.

The transform argument expects a callable transform object, so AutoAugment() must be instantiated.

4fill in blank

hard

Fill both blanks to create a composed transform with AutoAugment and normalization.

Computer Vision

transform = transforms.Compose([
    AutoAugment(policy=[1]),
    transforms.Normalize(mean=[2], std=[0.247, 0.243, 0.261])
])

Drag options to blanks, or click blank then click option'

AAutoAugmentPolicy.CIFAR10

B[0.4914, 0.4822, 0.4465]

C[0.5, 0.5, 0.5]

DAutoAugmentPolicy.IMAGENET

Attempts:

3 left

💡 Hint

Common Mistakes

Using ImageNet policy or wrong mean values for normalization.

The CIFAR10 policy is used for AutoAugment, and the mean values correspond to CIFAR10 dataset normalization.

5fill in blank

hard

Fill all three blanks to define a training loop that applies AutoAugment and computes accuracy.

Computer Vision

for images, labels in dataloader:
    images = images.to(device)
    labels = labels.to(device)
    outputs = model([1])
    loss = criterion(outputs, labels)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    _, predicted = outputs.[2](1)
    correct += (predicted == labels).[3]().item()

Drag options to blanks, or click blank then click option'

Aimages

Bmax

Csum

Dargmax

Attempts:

3 left

💡 Hint

Common Mistakes

Passing labels to the model instead of images.

Using argmax instead of max which returns both values and indices.

Using count() instead of sum() to count correct predictions.

The model input is images. The max function returns max values and indices, and sum counts correct predictions.

Practice

1. What is the main purpose of AutoAugment in computer vision?

easy

A. To convert images into grayscale before training

B. To reduce the size of the training dataset

C. To increase the number of layers in a neural network

D. To automatically find the best image transformations to improve model training

Solution

1. Step 1: Understand AutoAugment's goal

   AutoAugment searches for the best image changes (augmentations) to help models learn better.

2. Step 2: Compare options to this goal

   Only To automatically find the best image transformations to improve model training describes this automatic search for image transformations to improve training.

3. Final Answer:

   To automatically find the best image transformations to improve model training -> Option D

4. Quick Check:

   AutoAugment = automatic image transformation search [OK]

Hint: AutoAugment = automatic image changes for better training [OK]

Common Mistakes:

• Thinking AutoAugment reduces dataset size
• Confusing AutoAugment with model architecture changes
• Assuming it only converts images to grayscale

2. Which of the following is the correct way to apply AutoAugment using TensorFlow Addons in Python?

easy

A. tf.image.auto_augment(image)

B. tfa.image.auto_augment(image)

C. tfa.auto_augment(image)

D. tf.autoaugment(image)

Solution

1. Step 1: Identify the correct library and function

   TensorFlow Addons provides AutoAugment under the image module as tfa.image.auto_augment.

2. Step 2: Check each option's syntax

   Only tfa.image.auto_augment(image) uses the correct module and function name: tfa.image.auto_augment(image).

3. Final Answer:

   tfa.image.auto_augment(image) -> Option B

4. Quick Check:

   TensorFlow Addons image module = tfa.image.auto_augment [OK]

Hint: AutoAugment is in tfa.image, not tf or tfa root [OK]

Common Mistakes:

• Using tf.autoaugment instead of tfa.image.auto_augment
• Missing the image submodule in tfa
• Incorrect function name like auto_augment vs autoaugment

3. Given the following code snippet using AutoAugment, what will be the output shape of the augmented image?

import tensorflow as tf
import tensorflow_addons as tfa

image = tf.random.uniform([32, 32, 3])
augmented_image = tfa.image.auto_augment(image)
print(augmented_image.shape)

medium

A. (32, 32, 3)

B. (None, None, 3)

C. (32, 32)

D. (3, 32, 32)

Solution

1. Step 1: Check input image shape

   The input image has shape (32, 32, 3), meaning height=32, width=32, and 3 color channels.

2. Step 2: Understand AutoAugment output shape

   AutoAugment applies transformations but keeps the original image size and channels unchanged.

3. Final Answer:

   (32, 32, 3) -> Option A

4. Quick Check:

   AutoAugment keeps image shape same [OK]

Hint: AutoAugment changes pixels, not image size [OK]

Common Mistakes:

• Assuming output shape changes after augmentation
• Confusing channel order or missing channels
• Expecting batch dimension in output shape

4. You wrote this code to apply AutoAugment but get an error: AttributeError: module 'tensorflow_addons' has no attribute 'auto_augment'. What is the most likely fix?

medium

A. Import the image submodule and use tfa.image.auto_augment instead

B. Update TensorFlow to the latest version

C. Use tf.image.auto_augment instead of tfa

D. Restart the Python kernel

Solution

1. Step 1: Understand the error cause

   The error says tfa.auto_augment does not exist, meaning the function is not at the root of tensorflow_addons.

2. Step 2: Correct usage of AutoAugment in TensorFlow Addons

   The correct function is inside the image submodule: tfa.image.auto_augment.

3. Final Answer:

   Import the image submodule and use tfa.image.auto_augment instead -> Option A

4. Quick Check:

   Use tfa.image.auto_augment, not tfa.auto_augment [OK]

Hint: AutoAugment is in tfa.image, not tfa root [OK]

Common Mistakes:

• Trying to use tfa.auto_augment directly
• Assuming tf.image has AutoAugment
• Ignoring the need to import submodules

5. You want to improve your image classification model by using AutoAugment policies. Which approach best combines AutoAugment with training to maximize accuracy?

hard

A. Use AutoAugment only on validation images to test robustness

B. Apply AutoAugment once to the entire training dataset before training

C. Apply AutoAugment transformations on training images dynamically during each training epoch

D. Skip AutoAugment and increase model layers instead

Solution

1. Step 1: Understand dynamic augmentation benefits

   Applying AutoAugment dynamically during training shows varied images each epoch, helping the model generalize better.

2. Step 2: Compare static vs dynamic application

   Applying once (Apply AutoAugment once to the entire training dataset before training) limits variety; applying on validation (Use AutoAugment only on validation images to test robustness) is incorrect; increasing layers (Skip AutoAugment and increase model layers instead) is unrelated.

3. Final Answer:

   Apply AutoAugment transformations on training images dynamically during each training epoch -> Option C

4. Quick Check:

   Dynamic augmentation during training = best accuracy [OK]

Hint: Augment images freshly each epoch for best learning [OK]

Common Mistakes:

• Applying augmentation only once before training
• Augmenting validation data instead of training data
• Ignoring augmentation and changing model size