Why augmentation multiplies training data in Computer Vision - Model Pipeline Impact

Model Pipeline - Why augmentation multiplies training data

This pipeline shows how image augmentation creates more training data by changing images slightly. This helps the model learn better by seeing many versions of the same image.

Data Flow - 3 Stages

1Original Dataset

1000 images x 64x64 pixels x 3 color channels→Start with original images→1000 images x 64x64 pixels x 3 color channels

Image of a cat, 64x64 pixels, RGB

↓

2Augmentation

1000 images x 64x64 pixels x 3 color channels→Apply random flips, rotations, and brightness changes→5000 images x 64x64 pixels x 3 color channels

Original cat image flipped horizontally, rotated 15 degrees, brightness increased

↓

3Train/Test Split

5000 images x 64x64 pixels x 3 color channels→Split into training and testing sets→4000 training images, 1000 testing images

4000 augmented cat images for training, 1000 augmented images for testing

Training Trace - Epoch by Epoch

Loss
1.2 |**************
1.0 |**********
0.8 |********
0.6 |******
0.4 |****
0.2 |**
0.0 +----------------
     1  3  5  7  10 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning with high loss and low accuracy
3	0.8	0.65	Loss decreases and accuracy improves as model sees more augmented data
5	0.5	0.80	Model learns better features due to diverse augmented images
7	0.35	0.88	Loss continues to decrease, accuracy approaches high values
10	0.25	0.92	Model converges with low loss and high accuracy

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Convolutional Layer

Layer 3: Activation (ReLU)

Layer 4: Pooling Layer

Layer 5: Fully Connected Layer

Layer 6: Softmax

Model Quiz - 3 Questions

Why does augmentation multiply the training data?

A Because it removes bad images from the dataset

B Because it compresses images to smaller sizes

C Because it creates new images by changing originals

D Because it labels images automatically

Key Insight

Augmentation helps the model see many versions of the same image, making it learn better and generalize well. This increases the training data size without collecting new images.

Practice

1. Why does image augmentation multiply the training data in computer vision?

easy

A. Because it creates new images by changing existing ones

B. Because it deletes some images to reduce overfitting

C. Because it compresses images to save space

D. Because it labels images automatically

Solution

1. Step 1: Understand augmentation purpose

   Augmentation creates new images by applying changes like rotation or flipping to existing images.

2. Step 2: Connect augmentation to data size

   These new images increase the total number of training samples, effectively multiplying the dataset size.

3. Final Answer:

   Because it creates new images by changing existing ones -> Option A

4. Quick Check:

   Augmentation = new image versions [OK]

Hint: Augmentation makes new images from old ones [OK]

Common Mistakes:

• Thinking augmentation deletes images
• Confusing augmentation with compression
• Believing augmentation automatically labels data

2. Which of the following Python code snippets correctly applies horizontal flip augmentation using torchvision transforms?

easy

A. transform = transforms.FlipHorizontal()

B. transform = transforms.HorizontalFlip()

C. transform = transforms.RandomHorizontalFlip(p=1.0)

D. transform = transforms.RandomFlip(direction='horizontal')

Solution

1. Step 1: Recall torchvision syntax

   In torchvision, horizontal flip is done with RandomHorizontalFlip and a probability parameter.

2. Step 2: Check options for correct class and parameters

   Only transform = transforms.RandomHorizontalFlip(p=1.0) uses the correct class name and parameter format.

3. Final Answer:

   transform = transforms.RandomHorizontalFlip(p=1.0) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transform = transforms.RandomHorizontalFlip(p=1.0) [OK]

Hint: Look for RandomHorizontalFlip with p parameter [OK]

Common Mistakes:

• Using incorrect class names like HorizontalFlip
• Missing the probability parameter p
• Assuming FlipHorizontal exists in torchvision

3. Given this code snippet applying augmentation, what is the total number of images after augmentation if the original dataset has 100 images and each image is augmented with 3 different transformations?

medium

A. 300

B. 400

C. 100

D. 600

Solution

1. Step 1: Calculate augmented images per original

   Each original image produces 3 new augmented images plus the original itself, totaling 4 images per original.

2. Step 2: Multiply by original dataset size

   100 original images * 4 images each = 400 images total after augmentation.

3. Final Answer:

   400 -> Option B

4. Quick Check:

   (3 augmentations + 1 original) * 100 = 400 [OK]

Hint: Add original + augmentations, then multiply by dataset size [OK]

Common Mistakes:

• Counting only augmented images, ignoring originals
• Multiplying by 3 instead of 4
• Adding instead of multiplying

4. Identify the error in this augmentation code snippet and select the fix:

from torchvision import transforms
transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.RandomFlip(horizontal=true)
])

medium

A. Replace RandomFlip with RandomHorizontalFlip

B. Change RandomRotation(30) to RandomRotation(degrees=30)

C. Add p=0.5 to RandomFlip

D. No error, code is correct

Solution

1. Step 1: Check torchvision augmentation classes

   There is no RandomFlip class in torchvision; horizontal flip uses RandomHorizontalFlip.

2. Step 2: Identify correct fix

   Replacing RandomFlip with RandomHorizontalFlip fixes the error; other options are incorrect or unnecessary.

3. Final Answer:

   Replace RandomFlip with RandomHorizontalFlip -> Option A

4. Quick Check:

   Correct flip class = RandomHorizontalFlip [OK]

Hint: Use exact torchvision class names for flips [OK]

Common Mistakes:

• Assuming RandomFlip exists
• Changing rotation syntax unnecessarily
• Adding parameters to non-existent classes

5. You have a small dataset of 50 images. You want to multiply your training data by 5 times using augmentation. Which combination of augmentations is best to achieve this without losing original images?

hard

A. Apply 5 augmentations but discard original images

B. Only keep original images and train longer

C. Apply 2 augmentations and duplicate images twice

D. Apply 4 different augmentations per image plus keep original images

Solution

1. Step 1: Understand multiplication goal

   To multiply data by 5 times, total images after augmentation should be 50 * 5 = 250.

2. Step 2: Calculate images per original

   Keeping original plus 4 augmentations per image gives 5 images per original, totaling 250 images.

3. Step 3: Evaluate options

   Apply 4 different augmentations per image plus keep original images achieves the goal without losing original images; others either discard originals or don't reach 5x.

4. Final Answer:

   Apply 4 different augmentations per image plus keep original images -> Option D

5. Quick Check:

   Original + 4 augmentations = 5x data [OK]

Hint: Keep originals + 4 augmentations for 5x data [OK]

Common Mistakes:

• Discarding original images reduces data size
• Duplicating images without augmentation doesn't add variety
• Training longer without augmentation doesn't multiply data