Training an image classifier in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the right model for image classification

You want to train a model to classify images of cats and dogs. Which model architecture is best suited for this task?

A A simple linear regression model with no hidden layers

B A convolutional neural network (CNN) with several convolutional and pooling layers

C A recurrent neural network (RNN) designed for sequential data

D A k-nearest neighbors (KNN) model using raw pixel values as features

💡 Hint

Think about which model type is designed to capture spatial patterns in images.

CNNs are designed to detect patterns in images by using convolutional layers that scan for features like edges and shapes. Linear regression and RNNs are not suitable for image data, and KNN with raw pixels usually performs poorly.

❓ Hyperparameter

intermediate

Selecting the batch size for training

You are training an image classifier on a dataset of 10,000 images. Which batch size is most likely to balance training speed and model performance?

A Batch size of 32 or 64

B Batch size of 1 (stochastic gradient descent)

C Batch size of 10,000 (full batch gradient descent)

D Batch size of 5000

💡 Hint

Consider a batch size that allows efficient computation and stable updates.

Batch sizes like 32 or 64 are commonly used because they provide a good balance between noisy updates (small batches) and slow computation (very large batches). Batch size 1 is slow and noisy; full batch is slow and may not generalize well.

❓ Metrics

advanced

Evaluating model accuracy on imbalanced classes

You trained an image classifier on a dataset where 90% of images are class A and 10% are class B. The model predicts class A for all images. What is the accuracy and why is it misleading?

A Accuracy is 50%, indicating random guessing

B Accuracy is 10%, showing poor performance

C Accuracy is 90%, but the model fails to detect class B images

D Accuracy is 100%, meaning perfect classification

💡 Hint

Think about what happens if the model always predicts the majority class.

The model predicts class A for all images, so it is correct 90% of the time. However, it never detects class B, so accuracy is misleading. Other metrics like recall or F1-score are needed.

🔧 Debug

advanced

Identifying the cause of overfitting in training

You trained an image classifier and see training accuracy of 98% but validation accuracy of 60%. What is the most likely cause?

A The model is too complex and memorizes training data instead of generalizing

B The batch size is too large causing unstable training

C The learning rate is too low, preventing learning

D The dataset is too small causing underfitting

💡 Hint

Think about why training accuracy is high but validation accuracy is low.

High training accuracy and low validation accuracy usually means overfitting: the model memorizes training examples but does not generalize well to new data.

🧠 Conceptual

expert

Understanding transfer learning benefits

You want to train an image classifier but have only 500 labeled images. Which approach best improves model performance?

A Use a linear regression model on raw pixels

B Train a CNN from scratch with random weights on your dataset

C Use k-means clustering to label images automatically

D Use a pretrained CNN model and fine-tune it on your dataset

💡 Hint

Think about how to leverage knowledge from large datasets when you have few images.

Transfer learning uses a pretrained CNN trained on large datasets to extract useful features. Fine-tuning it on your small dataset improves performance compared to training from scratch.