Small dataset strategies in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load images from a directory using a common computer vision library.

Computer Vision

from tensorflow.keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(rescale=1./255)
data = datagen.flow_from_directory('[1]', target_size=(150, 150), batch_size=32, class_mode='binary')

Drag options to blanks, or click blank then click option'

Adataset/train

Bimages

Cdata

Dfolder

Attempts:

3 left

💡 Hint

Common Mistakes

Using a generic folder name that does not exist.

Not specifying the correct path to the image directory.

The directory path where training images are stored is usually specified. Here, 'dataset/train' is the correct folder path.

2fill in blank

medium

Complete the code to apply data augmentation to images to help with small datasets.

Computer Vision

datagen = ImageDataGenerator(rescale=1./255, rotation_range=[1], horizontal_flip=True)

Drag options to blanks, or click blank then click option'

A10

B180

C90

D40

Attempts:

3 left

💡 Hint

Common Mistakes

Using 90 or 180 degrees which may distort images too much.

Using too small rotation like 10 degrees which may not augment enough.

Rotation range of 40 degrees is a common augmentation to help models generalize better on small datasets.

3fill in blank

hard

Fix the error in the code to freeze the base model layers for transfer learning.

Computer Vision

base_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=False, weights='imagenet')
for layer in base_model.[1]:
    layer.trainable = False

Drag options to blanks, or click blank then click option'

Alayer

Blayers

Ctrainable

Dtrain

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'layer' which is a single layer, not iterable.

Using 'trainable' or 'train' which are not iterable attributes.

The base model's layers are accessed via the 'layers' attribute to freeze them.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps image filenames to their augmented versions.

Computer Vision

augmented_images = {filename: next(datagen.[1](image[None], batch_size=1))[0] for filename, image in images.items() if image.shape [2] (224, 224, 3)}

Drag options to blanks, or click blank then click option'

Aflow

Bshape

C==

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'resize' which is not a method of ImageDataGenerator.

Using 'shape' as a method instead of an attribute.

'flow' generates augmented images from the original image, and '==' checks if the image shape matches the target size.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that filters images by size and applies augmentation.

Computer Vision

filtered_augmented = {filename: next(datagen.[1](image[None], batch_size=1))[0] for filename, image in images.items() if image.[2][0] [3] 224}

Drag options to blanks, or click blank then click option'

Aflow

Bshape

C>=

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>=' which filters out larger images.

Using 'resize' instead of 'flow' for augmentation.

'flow' generates augmented images, 'shape' accesses the image dimensions, and '>=' filters images with width at least 224 pixels.

Practice

1. Which of the following is a common strategy to improve model performance when you have a small image dataset?

easy

A. Train a deep model from scratch without any pre-trained weights

B. Use data augmentation to create more training images

C. Ignore validation to use all data for training

D. Reduce image resolution to save memory only

Solution

1. Step 1: Understand small dataset challenges

   Small datasets often cause models to overfit and perform poorly on new data.

2. Step 2: Identify effective strategies

   Data augmentation creates new images by modifying existing ones, increasing data variety and helping the model generalize better.

3. Final Answer:

   Use data augmentation to create more training images -> Option B

4. Quick Check:

   Data augmentation = More data variety [OK]

Hint: More data variety helps small datasets [OK]

Common Mistakes:

• Training from scratch causes overfitting
• Ignoring validation hides model issues
• Reducing resolution alone doesn't add data

2. Which code snippet correctly applies data augmentation using the Python library torchvision.transforms?

easy

A. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()])

B. transforms.RandomCrop(32, 32)

C. transforms.ToTensor(), transforms.Normalize()

D. transforms.Resize(256)

Solution

1. Step 1: Recognize data augmentation syntax

   Data augmentation requires combining multiple transforms, usually with Compose.

2. Step 2: Check which option uses Compose with augmentation

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) uses Compose with RandomHorizontalFlip (augmentation) and ToTensor (conversion), which is correct.

3. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) -> Option A

4. Quick Check:

   Compose + augmentation = transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) [OK]

Hint: Use Compose to combine augmentations [OK]

Common Mistakes:

• Using single transform without Compose
• Missing ToTensor conversion
• Using only resizing without augmentation

3. Consider this Python code using transfer learning with PyTorch:

import torchvision.models as models
model = models.resnet18(pretrained=True)
for param in model.parameters():
    param.requires_grad = False
model.fc = torch.nn.Linear(512, 2)

What does this code do?

medium

A. Trains all layers of ResNet18 from scratch

B. Unfreezes all layers for fine-tuning

C. Freezes all layers except the last fully connected layer

D. Removes the last layer without replacement

Solution

1. Step 1: Analyze parameter freezing

   The loop sets requires_grad=False for all parameters, freezing them during training.

2. Step 2: Check the last layer replacement

   The last fully connected layer (fc) is replaced with a new Linear layer, which by default has requires_grad=True.

3. Final Answer:

   Freezes all layers except the last fully connected layer -> Option C

4. Quick Check:

   Freeze all but last layer = Freezes all layers except the last fully connected layer [OK]

Hint: Freeze parameters, then replace last layer [OK]

Common Mistakes:

• Assuming all layers are trainable
• Not noticing last layer replacement
• Confusing freezing with unfreezing

4. You wrote this code to augment images but get an error:

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

What is the error and how to fix it?

medium

A. Transforms must be applied outside Compose

B. RandomRotation requires degrees as a tuple, fix by using (0,30)

C. Compose should be replaced by Sequential

D. Missing parentheses after ToTensor; fix by using transforms.ToTensor()

Solution

1. Step 1: Identify the error in ToTensor usage

   transforms.ToTensor is a class, missing parentheses means it's not called, causing an error.

2. Step 2: Correct the syntax

   Add parentheses to call ToTensor: transforms.ToTensor()

3. Final Answer:

   Missing parentheses after ToTensor; fix by using transforms.ToTensor() -> Option D

4. Quick Check:

   Call ToTensor() as function [OK]

Hint: Call transform classes with () [OK]

Common Mistakes:

• Forgetting parentheses on transform classes
• Misusing Compose with wrong functions
• Incorrect argument types for RandomRotation

5. You have only 100 labeled images for a classification task. Which combined approach best improves model accuracy?

hard

A. Use transfer learning with a pre-trained model and apply data augmentation

B. Train a deep CNN from scratch with no augmentation

C. Use only data augmentation without pre-trained weights

D. Increase batch size to 512 and train for fewer epochs

Solution

1. Step 1: Understand small dataset limits

   With only 100 images, training deep models from scratch risks overfitting and poor generalization.

2. Step 2: Combine transfer learning and augmentation

   Transfer learning uses knowledge from large datasets, and augmentation increases data variety, both improving accuracy.

3. Final Answer:

   Use transfer learning with a pre-trained model and apply data augmentation -> Option A

4. Quick Check:

   Transfer learning + augmentation = Best for small data [OK]

Hint: Combine pre-trained models with augmentation [OK]

Common Mistakes:

• Training from scratch with little data
• Relying on augmentation alone
• Using too large batch size causing poor learning