Data augmentation in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - Data augmentation

Which metric matters for Data Augmentation and WHY

Data augmentation helps models learn better by showing more varied examples. The key metrics to watch are validation accuracy and validation loss. These show if the model is improving on new, unseen data, not just memorizing training data. A lower validation loss and higher validation accuracy mean the augmentation is helping the model generalize well.

Confusion Matrix Example

      Actual \ Predicted | Positive | Negative
      -------------------|----------|---------
      Positive           |    85    |   15
      Negative           |    10    |   90
    

This confusion matrix shows the model's predictions after training with data augmentation. The numbers add up to 200 samples. From this, we can calculate precision, recall, and F1 score to see how well the model performs.

Precision vs Recall Tradeoff with Data Augmentation

Data augmentation can help improve both precision and recall by making the model see more varied examples. For example, in a face recognition app, high precision means fewer wrong matches, while high recall means fewer missed faces. Augmentation helps balance these by reducing overfitting and making the model robust to changes like lighting or angle.

Good vs Bad Metric Values for Data Augmentation

• Good: Validation accuracy steadily improves or stays stable, validation loss decreases, and confusion matrix shows balanced true positives and true negatives.
• Bad: Validation accuracy drops or fluctuates wildly, validation loss increases, or confusion matrix shows many false positives or false negatives, indicating the model is confused despite augmentation.

Common Pitfalls in Metrics with Data Augmentation

• Accuracy Paradox: High accuracy but poor recall or precision can hide problems. For example, if data is imbalanced, accuracy alone is misleading.
• Data Leakage: Augmented data too similar to test data can inflate metrics falsely.
• Overfitting Indicators: Training accuracy much higher than validation accuracy means augmentation might not be enough or is not diverse.

Self Check

Your model trained with data augmentation has 98% accuracy but only 12% recall on the positive class (e.g., fraud). Is it good for production?
No. The low recall means the model misses most positive cases, which is critical in fraud detection. Despite high accuracy, the model fails to catch important examples. You should improve augmentation or model to raise recall.

Key Result

Validation accuracy and loss best show if data augmentation helps the model generalize well.

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