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.

Practice

1. What is the main goal when training an image classifier?

easy

A. To convert images into text

B. To teach the model to recognize different categories of images

C. To increase the size of the images

D. To remove colors from images

Solution

1. Step 1: Understand the purpose of image classification

   Image classification means teaching a model to identify what category an image belongs to, like cats or dogs.

2. Step 2: Identify the correct goal

   The goal is to train the model to recognize image categories, not to change image size or color.

3. Final Answer:

   To teach the model to recognize different categories of images -> Option B

4. Quick Check:

   Image classification = recognize categories [OK]

Hint: Remember: Classifier means sorting images into groups [OK]

Common Mistakes:

• Confusing image classification with image editing
• Thinking the goal is to change image colors
• Assuming the model outputs text instead of categories

2. Which code snippet correctly adds a convolutional layer in a TensorFlow Keras model?

easy

A. model.add(MaxPooling2D(32, (3, 3)))

B. model.add(Dense(32, (3, 3), activation='relu'))

C. model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 3)))

D. model.add(Flatten(32, (3, 3)))

Solution

1. Step 1: Identify the correct layer type for convolution

   Conv2D is the correct layer to extract image features using filters.

2. Step 2: Check the syntax for Conv2D

   The correct syntax includes number of filters, kernel size, activation, and input shape for the first layer.

3. Final Answer:

   model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 3))) -> Option C

4. Quick Check:

   Conv2D with filters and kernel size = model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 3))) [OK]

Hint: Conv2D needs filters, kernel size, and activation [OK]

Common Mistakes:

• Using Dense instead of Conv2D for images
• Passing wrong arguments to Flatten or MaxPooling2D
• Missing input_shape in first Conv2D layer

3. Given this code, what will be the printed accuracy after training?

import tensorflow as tf
from tensorflow.keras import layers, models

model = models.Sequential([
  layers.Conv2D(16, (3,3), activation='relu', input_shape=(28,28,1)),
  layers.Flatten(),
  layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

import numpy as np
x_train = np.random.random((100, 28, 28, 1))
y_train = np.random.randint(0, 10, 100)

history = model.fit(x_train, y_train, epochs=1, verbose=0)
print(f"Accuracy: {history.history['accuracy'][0]:.2f}")

medium

A. Accuracy will be around 0.10 (random guessing)

B. Accuracy will be close to 1.00 (perfect)

C. Code will raise a syntax error

D. Accuracy will be exactly 0.50

Solution

1. Step 1: Understand the data and labels

   The training data is random noise and labels are random integers from 0 to 9, so no real pattern exists.

2. Step 2: Predict model accuracy on random data

   Since the model cannot learn meaningful features, accuracy will be close to random guessing, about 10% for 10 classes.

3. Final Answer:

   Accuracy will be around 0.10 (random guessing) -> Option A

4. Quick Check:

   Random data accuracy ≈ 1/number_of_classes = 0.10 [OK]

Hint: Random labels mean accuracy near chance level [OK]

Common Mistakes:

• Expecting high accuracy on random data
• Thinking code has syntax errors
• Assuming accuracy is always 0.5

4. This code tries to train an image classifier but throws an error. What is the problem?

model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(32, 3, activation='relu'))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)

Assume x_train shape is (100, 28, 28, 1).

medium

A. Missing input_shape in first Conv2D layer

B. Dense layer should come before Conv2D

C. Loss function is incorrect for classification

D. Optimizer 'adam' is not supported

Solution

1. Step 1: Check Conv2D layer input requirements

   The first Conv2D layer must specify input_shape to know the input image size.

2. Step 2: Identify missing input_shape

   Since input_shape is missing, TensorFlow cannot infer input dimensions, causing an error.

3. Final Answer:

   Missing input_shape in first Conv2D layer -> Option A

4. Quick Check:

   First Conv2D needs input_shape [OK]

Hint: First Conv2D layer always needs input_shape [OK]

Common Mistakes:

• Thinking Dense must come before Conv2D
• Confusing loss function for classification
• Believing 'adam' optimizer is invalid

5. You want to improve your image classifier's accuracy on a small dataset. Which approach is best?

hard

A. Remove the activation functions from all layers

B. Reduce the number of convolutional layers to one

C. Train for only one epoch to avoid overfitting

D. Add data augmentation like rotations and flips during training

Solution

1. Step 1: Understand challenges with small datasets

   Small datasets can cause overfitting, where the model memorizes instead of generalizing.

2. Step 2: Identify best method to improve generalization

   Data augmentation creates new image variations, helping the model learn better and improve accuracy.

3. Final Answer:

   Add data augmentation like rotations and flips during training -> Option D

4. Quick Check:

   Data augmentation improves small dataset accuracy [OK]

Hint: Use data augmentation to expand small datasets [OK]

Common Mistakes:

• Reducing layers too much loses learning power
• Training only one epoch usually underfits
• Removing activations breaks model learning