Data augmentation in PyTorch - Model Pipeline Trace

Model Pipeline - Data augmentation

Data augmentation is a technique to create more training data by making small changes to existing images. This helps the model learn better by seeing many versions of the same image.

Data Flow - 4 Stages

1Original dataset

1000 images x 3 channels x 32 height x 32 width→Load raw images→1000 images x 3 x 32 x 32

Image of a cat with RGB channels

↓

2Apply random horizontal flip

1000 images x 3 x 32 x 32→Flip images horizontally with 50% chance→1000 images x 3 x 32 x 32

Cat image flipped left to right

↓

3Apply random rotation

1000 images x 3 x 32 x 32→Rotate images randomly between -15 and 15 degrees→1000 images x 3 x 32 x 32

Cat image rotated slightly clockwise

↓

4Normalize images

1000 images x 3 x 32 x 32→Scale pixel values to mean=0.5 and std=0.5→1000 images x 3 x 32 x 32

Pixel values adjusted to range around zero

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	Loss lowers and accuracy rises steadily
5	0.45	0.85	Model shows good learning progress with augmentation

Prediction Trace - 5 Layers

Layer 1: Input image

Layer 2: Random horizontal flip

Layer 3: Random rotation

Layer 4: Normalization

Layer 5: Model prediction

Model Quiz - 3 Questions

Why do we apply random horizontal flip during data augmentation?

A To convert images to grayscale

B To help the model learn from different views of the same image

C To reduce the image size

D To increase the number of image channels

Key Insight

Data augmentation creates varied versions of images, helping the model learn more robust features and improving accuracy by reducing overfitting.

Practice

1. What is the main purpose of data augmentation in PyTorch training pipelines?

easy

A. To reduce the size of the training dataset

B. To create new training data by modifying existing data

C. To speed up model training by skipping data preprocessing

D. To convert data into a different file format

Solution

1. Step 1: Understand data augmentation concept

   Data augmentation means making new training examples by changing existing ones, like flipping or rotating images.

2. Step 2: Identify the purpose in training

   This helps the model see more variety and avoid memorizing only the original data, improving learning.

3. Final Answer:

   To create new training data by modifying existing data -> Option B

4. Quick Check:

   Data augmentation = create new data [OK]

Hint: Data augmentation means changing data to get more examples [OK]

Common Mistakes:

• Thinking it reduces dataset size
• Confusing augmentation with speeding training
• Believing it changes file formats

2. Which of the following is the correct way to apply a random horizontal flip to an image tensor using torchvision transforms?

easy

A. transforms.RandomHorizontalFlip(p=0.5)

B. transforms.HorizontalFlip(prob=0.5)

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

D. transforms.FlipHorizontal(0.5)

Solution

1. Step 1: Recall torchvision transform syntax

   The correct transform for horizontal flip is RandomHorizontalFlip with a probability parameter p.

2. Step 2: Match correct syntax

   transforms.RandomHorizontalFlip(p=0.5) uses transforms.RandomHorizontalFlip(p=0.5), which is the exact PyTorch syntax.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=0.5) -> Option A

4. Quick Check:

   Correct transform name and parameter = C [OK]

Hint: Look for 'RandomHorizontalFlip' with p= probability [OK]

Common Mistakes:

• Using wrong transform names
• Using 'prob' instead of 'p'
• Incorrect parameter names or missing parentheses

3. What will be the output shape of the image tensor after applying the following transform?

transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.ToTensor()
])

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

medium

A. [3, H, W] where H and W are original image height and width

B. [H, W, 3] where H and W are original image height and width

C. [1, H, W] grayscale image shape

D. [3, 30, 30] fixed size after rotation

Solution

1. Step 1: Understand transforms.Compose and RandomRotation

   RandomRotation rotates the image but keeps the original size (height and width). ToTensor converts the image to a tensor with shape [channels, height, width].

2. Step 2: Determine output tensor shape

   Since the image is color (3 channels), the tensor shape will be [3, H, W], where H and W are original height and width.

3. Final Answer:

   [3, H, W] where H and W are original image height and width -> Option A

4. Quick Check:

   Rotation keeps size, ToTensor outputs [3, H, W] [OK]

Hint: ToTensor outputs [channels, height, width] shape [OK]

Common Mistakes:

• Confusing channel order as last dimension
• Assuming rotation changes image size
• Thinking output is grayscale shape

4. Identify the error in this PyTorch data augmentation code snippet:

transform = transforms.Compose([
    transforms.RandomHorizontalFlip(prob=0.5),
    transforms.RandomRotation(degrees=45),
    transforms.ToTensor()
])

medium

A. RandomRotation degrees must be a tuple, not a single number

B. ToTensor should come before RandomRotation

C. RandomHorizontalFlip should use keyword argument p=0.5

D. Compose cannot combine multiple transforms

Solution

1. Step 1: Check RandomHorizontalFlip usage

   RandomHorizontalFlip requires the probability argument as p=0.5, not prob=0.5.

2. Step 2: Verify other transforms

   RandomRotation accepts a single number for degrees, ToTensor can come last, and Compose supports multiple transforms.

3. Final Answer:

   RandomHorizontalFlip should use keyword argument p=0.5 -> Option C

4. Quick Check:

   Correct argument name = p [OK]

Hint: Check argument names carefully in transform constructors [OK]

Common Mistakes:

• Passing positional argument instead of keyword
• Thinking degrees must be tuple
• Misordering transforms in Compose

5. You want to augment a dataset of images to improve model robustness. Which combination of transforms would best increase variety without changing image size or color channels?

Options:
A) RandomHorizontalFlip(p=0.5) + RandomRotation(15) + ColorJitter(brightness=0.2)
B) RandomResizedCrop(size=224) + Grayscale(num_output_channels=1)
C) RandomVerticalFlip(p=1.0) + RandomRotation(90) + ToTensor()
D) Resize(128) + RandomCrop(64) + RandomHorizontalFlip(p=0.5)

hard

A. Resize and crop to smaller size (changes image size)

B. RandomResizedCrop and converting to grayscale (changes size and channels)

C. Vertical flip and 90-degree rotation (may change orientation drastically)

D. RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness

Solution

1. Step 1: Analyze each option's effect on size and channels

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness flips, rotates slightly, and changes brightness without resizing or changing channels. RandomResizedCrop and converting to grayscale (changes size and channels) changes size and converts to grayscale. Vertical flip and 90-degree rotation (may change orientation drastically) rotates 90 degrees and flips vertically, which changes orientation drastically. Resize and crop to smaller size (changes image size) resizes and crops, changing size.

2. Step 2: Choose the option that keeps size and channels but increases variety

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness best fits the requirement by augmenting with flips, small rotations, and brightness changes without altering size or channels.

3. Final Answer:

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness -> Option D

4. Quick Check:

   Keep size and channels, add mild augmentations = A [OK]

Hint: Pick augmentations that don't resize or change color channels [OK]

Common Mistakes:

• Choosing transforms that resize images
• Converting images to grayscale unintentionally
• Using large rotations that distort orientation