Augmentation policy search (AutoAugment) in Computer Vision - Model Pipeline Trace

Model Pipeline - Augmentation policy search (AutoAugment)

This pipeline automatically finds the best ways to change images to help a model learn better. It tries different image changes, like flipping or color shifts, to improve the model's ability to recognize objects.

Data Flow - 5 Stages

1Raw Image Dataset

50000 images x 32 x 32 x 3→Original CIFAR-10 images→50000 images x 32 x 32 x 3

Image of a cat with RGB colors

↓

2Augmentation Policy Search

50000 images x 32 x 32 x 3→Apply different image transformations like rotate, shear, color adjust with varying strengths to find best policies→50000 images x 32 x 32 x 3 (augmented)

Image rotated 15 degrees and brightness increased by 20%

↓

3Train/Test Split

50000 images x 32 x 32 x 3→Split dataset into training (45000) and validation (5000)→45000 images x 32 x 32 x 3 (train), 5000 images x 32 x 32 x 3 (validation)

Training image of a dog, validation image of a truck

↓

4Model Training

45000 images x 32 x 32 x 3→Train convolutional neural network on augmented images→Trained model weights

CNN learns to recognize objects better with augmented images

↓

5Validation Evaluation

5000 images x 32 x 32 x 3→Evaluate model accuracy on validation set→Accuracy score (percentage)

Model achieves 88% accuracy on validation images

Training Trace - Epoch by Epoch

Loss
1.2 |****
1.0 |***
0.8 |**
0.6 |**
0.4 |*
0.2 |
    +----------------
     1 5 10 15 20 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.20	0.55	Model starts learning with moderate accuracy
5	0.75	0.75	Loss decreases and accuracy improves as model learns
10	0.50	0.85	Model shows strong learning with good accuracy
15	0.40	0.89	Loss continues to decrease, accuracy nearing 90%
20	0.35	0.91	Model converges with high accuracy and low loss

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Augmentation Policy Applied

Layer 3: Convolutional Layer

Layer 4: Pooling Layer

Layer 5: Fully Connected Layer

Layer 6: Softmax Activation

Model Quiz - 3 Questions

What is the main purpose of the augmentation policy search step?

A To split the dataset into training and validation sets

B To find the best image changes that help the model learn better

C To evaluate the model accuracy on test data

D To reduce the size of images for faster training

Key Insight

AutoAugment helps the model learn better by automatically finding the best image changes. This makes the model more accurate and robust by showing it many useful variations of the images during training.

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