Albumentations integration in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - Albumentations integration

Which metric matters for Albumentations integration and WHY

Albumentations is a tool to change images before training. It helps the model see many versions of the same picture. This makes the model better at understanding new pictures. The key metric to watch is validation accuracy or validation loss. This shows if the model is learning well on new, unseen images. If accuracy goes up or loss goes down on validation data, Albumentations is helping.

Confusion matrix example

Imagine a model classifying cats and dogs. After training with Albumentations, the confusion matrix might look like this:

          Predicted Cat   Predicted Dog
Actual Cat       45             5
Actual Dog        7            43

Total samples = 100

Here, true positives (TP) for cats = 45, false positives (FP) for cats = 7, false negatives (FN) for cats = 5, true negatives (TN) for cats = 43.

Precision vs Recall tradeoff with Albumentations

Albumentations helps the model see more varied images, which can improve both precision and recall.

• Precision means when the model says "this is a cat," how often it is right.
• Recall means how many actual cats the model finds.

For example, if Albumentations creates many good variations, the model learns better features and can find more cats (higher recall) without making many mistakes (high precision).

Good vs Bad metric values for Albumentations use

Good: Validation accuracy improves by 3-5% compared to no augmentation. Precision and recall both above 0.8. Loss decreases steadily.

Bad: Validation accuracy stays the same or drops. Precision or recall below 0.5. Loss fluctuates or increases, showing model confusion.

Common pitfalls with Albumentations metrics

• Overfitting: Training accuracy very high but validation accuracy low means augmentation may be insufficient or incorrect.
• Data leakage: Augmenting validation data by mistake inflates validation accuracy falsely.
• Wrong augmentations: Using augmentations that distort images too much can confuse the model, hurting metrics.
• Ignoring metric trends: Only looking at training loss without validation metrics can hide problems.

Self-check question

Your model trained with Albumentations has 98% training accuracy but only 12% recall on the cat class in validation. Is this good?

Answer: No. The model is not finding most cats in new images (low recall). This means it misses many cats, so Albumentations or training needs adjustment.

Key Result

Validation accuracy and recall are key to check if Albumentations helps the model learn better on new images.

Practice

1. What is the main purpose of using Albumentations in PyTorch image processing pipelines?

easy

A. To apply image transformations that improve model learning

B. To train the model faster without changing images

C. To convert tensors back to images

D. To save models after training

Solution

1. Step 1: Understand Albumentations role

   Albumentations is a library used to apply image transformations like flips, rotations, and brightness changes.

2. Step 2: Connect transformations to model learning

   These transformations help the model see varied images, improving its ability to learn and generalize.

3. Final Answer:

   To apply image transformations that improve model learning -> Option A

4. Quick Check:

   Albumentations = image transformations [OK]

Hint: Albumentations changes images to help models learn better [OK]

Common Mistakes:

• Thinking Albumentations speeds up training directly
• Confusing Albumentations with model saving tools
• Believing it converts tensors back to images

2. Which of the following is the correct way to combine multiple Albumentations transforms in PyTorch?

easy

A. transforms = A.Compose([A.Resize(128, 128), A.HorizontalFlip()])

B. transforms = A.Sequential([A.Resize(128, 128), A.HorizontalFlip()])

C. transforms = A.Transforms([A.Resize(128, 128), A.HorizontalFlip()])

D. transforms = A.Pipeline([A.Resize(128, 128), A.HorizontalFlip()])

Solution

1. Step 1: Recall Albumentations syntax for combining transforms

   Albumentations uses Compose to combine multiple transformations into one pipeline.

2. Step 2: Check the options for correct function name

   Only A.Compose is the correct method; others like Sequential, Transforms, Pipeline do not exist in Albumentations.

3. Final Answer:

   transforms = A.Compose([A.Resize(128, 128), A.HorizontalFlip()]) -> Option A

4. Quick Check:

   Use Compose to combine transforms [OK]

Hint: Use Compose to combine Albumentations transforms [OK]

Common Mistakes:

• Using Sequential or Pipeline instead of Compose
• Misspelling Compose or using wrong method names
• Not passing a list of transforms inside Compose

3. Given the following code snippet, what will be the shape of the tensor after applying the transform?

import albumentations as A
from albumentations.pytorch import ToTensorV2

transform = A.Compose([
    A.Resize(64, 64),
    A.HorizontalFlip(p=1.0),
    ToTensorV2()
])

image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
transformed = transform(image=image)
tensor = transformed['image']
print(tensor.shape)

medium

A. torch.Size([3, 100, 100])

B. torch.Size([64, 64, 3])

C. torch.Size([3, 64, 64])

D. torch.Size([100, 100, 3])

Solution

1. Step 1: Analyze the transformations applied

   The image is resized to 64x64 pixels with 3 color channels, then flipped horizontally, and finally converted to a tensor.

2. Step 2: Understand ToTensorV2 output shape

   ToTensorV2 converts the image to a PyTorch tensor with shape (channels, height, width), so shape becomes (3, 64, 64).

3. Final Answer:

   torch.Size([3, 64, 64]) -> Option C

4. Quick Check:

   Resize + ToTensorV2 = (3, height, width) [OK]

Hint: ToTensorV2 outputs (channels, height, width) tensors [OK]

Common Mistakes:

• Confusing channel order with last dimension
• Ignoring resize effect on shape
• Expecting original image shape after transform

4. Identify the error in this Albumentations transform code snippet:

transform = A.Compose([
    A.Resize(128, 128),
    A.RandomBrightnessContrast(),
    ToTensorV2
])

medium

A. RandomBrightnessContrast requires parameters

B. Compose should be replaced with Sequential

C. Resize should be called with a tuple, not two arguments

D. ToTensorV2 is missing parentheses to call it

Solution

1. Step 1: Check each transform syntax

   Resize and RandomBrightnessContrast are correctly called with parentheses. ToTensorV2 is missing parentheses, so it's a reference, not a call.

2. Step 2: Confirm correct usage of ToTensorV2

   ToTensorV2 must be called as ToTensorV2() to create the transform instance.

3. Final Answer:

   ToTensorV2 is missing parentheses to call it -> Option D

4. Quick Check:

   Always call ToTensorV2() with parentheses [OK]

Hint: Always add () after ToTensorV2 to create transform [OK]

Common Mistakes:

• Forgetting parentheses on ToTensorV2
• Thinking Resize needs a tuple instead of two ints
• Replacing Compose with non-existent Sequential

5. You want to apply Albumentations transforms to a dataset and ensure the output tensors are normalized and ready for a PyTorch model. Which of the following code snippets correctly integrates Albumentations with normalization and tensor conversion?

hard

A. transform = A.Compose([
A.Resize(128, 128),
ToTensorV2(),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])

B. transform = A.Compose([
A.Resize(128, 128),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
ToTensorV2()
])

C. transform = A.Compose([
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
ToTensorV2(),
A.Resize(128, 128)
])

D. transform = A.Compose([
ToTensorV2(),
A.Resize(128, 128),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])

Solution

1. Step 1: Understand Albumentations transform order

   Resize should happen first to set image size, then Normalize to scale pixel values, and finally ToTensorV2 to convert to tensor.

2. Step 2: Check each option's order

   Only transform = A.Compose([ A.Resize(128, 128), A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), ToTensorV2() ]) applies Resize, then Normalize, then ToTensorV2 in correct order. Others apply Normalize or ToTensorV2 too early or in wrong order.

3. Final Answer:

   transform = A.Compose([ A.Resize(128, 128), A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), ToTensorV2() ]) -> Option B

4. Quick Check:

   Resize -> Normalize -> ToTensorV2 order [OK]

Hint: Normalize before ToTensorV2, Resize first [OK]

Common Mistakes:

• Normalizing after ToTensorV2 instead of before
• Applying Resize after ToTensorV2
• Forgetting to call ToTensorV2() with parentheses