Image augmentation transforms in Computer Vision - Model Pipeline Trace

Model Pipeline - Image augmentation transforms

This pipeline shows how image data is changed using augmentation transforms to help a model learn better. Augmentation creates new images by flipping, rotating, or changing brightness, so the model sees more variety and becomes stronger.

Data Flow - 5 Stages

1Original Images

1000 images x 64 x 64 x 3→Raw image data loaded from dataset→1000 images x 64 x 64 x 3

An image of a cat with size 64x64 pixels and 3 color channels (RGB)

↓

2Random Horizontal Flip

1000 images x 64 x 64 x 3→Flip each image horizontally with 50% chance→1000 images x 64 x 64 x 3

Cat image flipped left to right or kept as is

↓

3Random Rotation

1000 images x 64 x 64 x 3→Rotate images randomly between -15 to +15 degrees→1000 images x 64 x 64 x 3

Cat image rotated slightly clockwise or counterclockwise

↓

4Random Brightness Adjustment

1000 images x 64 x 64 x 3→Change brightness randomly by ±20%→1000 images x 64 x 64 x 3

Cat image appears lighter or darker

↓

5Augmented Images

1000 images x 64 x 64 x 3→Combined augmentations applied to increase data variety→1000 images x 64 x 64 x 3

Cat images with flips, rotations, and brightness changes

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.55|*
0.45| 
    +------------
    Epochs 1 to 5

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning with high loss and low accuracy
2	0.9	0.60	Loss decreases and accuracy improves as model learns
3	0.7	0.72	Model continues to improve with augmented data
4	0.55	0.80	Augmentation helps model generalize better
5	0.45	0.85	Loss lowers steadily and accuracy reaches good level

Prediction Trace - 5 Layers

Layer 1: Input Image

Layer 2: Random Horizontal Flip

Layer 3: Random Rotation

Layer 4: Random Brightness Adjustment

Layer 5: Model Input

Model Quiz - 3 Questions

What is the main purpose of applying image augmentation transforms?

A To make images black and white

B To increase the variety of training images

C To reduce the size of the dataset

D To remove noise from images

Key Insight

Image augmentation helps the model see many different versions of the same image. This variety teaches the model to recognize objects better in new, unseen pictures, improving accuracy and reducing overfitting.

Practice

1. What is the main purpose of image augmentation in training machine learning models?

easy

A. To reduce the size of the training dataset

B. To remove noise from images

C. To create more varied training images by modifying originals

D. To convert images to grayscale only

Solution

1. Step 1: Understand image augmentation

   Image augmentation means making small changes to original images to create new ones.

2. Step 2: Purpose in training

   This helps models see more variety and learn better, avoiding overfitting.

3. Final Answer:

   To create more varied training images by modifying originals -> Option C

4. Quick Check:

   Image augmentation = create varied images [OK]

Hint: Augmentation means changing images to get more training data [OK]

Common Mistakes:

• Thinking augmentation reduces dataset size
• Confusing augmentation with noise removal
• Assuming augmentation only changes color

2. Which of the following is the correct way to apply a horizontal flip using PyTorch's torchvision transforms?

easy

A. transforms.RandomHorizontalFlip(p=1.0)

B. transforms.HorizontalFlip()

C. transforms.FlipHorizontal()

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

Solution

1. Step 1: Recall torchvision syntax

   PyTorch uses transforms.RandomHorizontalFlip(p=probability) to flip images horizontally.

2. Step 2: Check options

   Only transforms.RandomHorizontalFlip(p=1.0) matches the correct function and parameter style.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=1.0) -> Option A

4. Quick Check:

   Correct PyTorch flip = RandomHorizontalFlip [OK]

Hint: Look for 'RandomHorizontalFlip' with probability parameter [OK]

Common Mistakes:

• Using non-existent transform names
• Missing the probability parameter
• Confusing horizontal with vertical flip

3. Given the following code snippet using torchvision transforms, what is the output image size after applying the transforms?

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.RandomCrop(100),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
output = transform(image)
print(output.shape)

medium

A. [3, 128, 128]

B. [3, 100, 100]

C. [1, 100, 100]

D. [3, 228, 228]

Solution

1. Step 1: Analyze each transform step

   First, image is resized to 128x128 pixels with 3 color channels (RGB). Then a random crop of size 100x100 is taken.

2. Step 2: Determine output tensor shape

   After cropping, the image size is 100x100 with 3 channels. ToTensor() converts it to a tensor with shape [channels, height, width] = [3, 100, 100].

3. Final Answer:

   [3, 100, 100] -> Option B

4. Quick Check:

   Resize then crop = final size 100x100 [OK]

Hint: Resize then crop means output size = crop size [OK]

Common Mistakes:

• Ignoring the crop step size
• Confusing channel dimension with batch size
• Assuming crop keeps original size

4. The following code is intended to rotate an image by 45 degrees using torchvision transforms, but it raises an error. What is the mistake?

transform = transforms.Compose([
    transforms.Rotate(45),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
output = transform(image)

medium

A. transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation

B. The angle 45 must be in radians, not degrees

C. ToTensor must come before Rotate

D. Image.open returns a tensor, so transform fails

Solution

1. Step 1: Check torchvision transform names

   There is no transforms.Rotate class. Rotation is done with transforms.RandomRotation or using functional API.

2. Step 2: Identify correct usage

   To rotate by a fixed angle, use transforms.RandomRotation([45, 45]) or transforms.functional.rotate. The code as is will cause an AttributeError.

3. Final Answer:

   transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation -> Option A

4. Quick Check:

   No transforms.Rotate in torchvision [OK]

Hint: Check transform names carefully; Rotate is not a direct class [OK]

Common Mistakes:

• Using non-existent transform classes
• Confusing degrees and radians
• Wrong order of transforms

5. You want to augment a dataset of images to improve model robustness. Which combination of transforms would best simulate real-world variations while keeping image size constant?

hard

A. transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128)

B. transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only

C. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor()

D. transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2)

Solution

1. Step 1: Understand augmentation goals

   We want to simulate real-world changes like size, flip, and color while keeping output size fixed.

2. Step 2: Evaluate options

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) resizes and crops randomly to 224x224, flips horizontally, and changes brightness/contrast, all common augmentations that keep size constant.

3. Step 3: Check other options

   transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only flips vertically and crops but lacks color changes. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor() changes size unpredictably and transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128) resizes after cropping, changing size.

4. Final Answer:

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) -> Option D

5. Quick Check:

   Best augmentations keep size fixed and add variety [OK]

Hint: Pick transforms that keep size fixed and add flip + color changes [OK]

Common Mistakes:

• Choosing transforms that change image size unpredictably
• Ignoring color augmentations
• Using only vertical flips which are less common