Model evaluation best practices in Computer Vision - Model Pipeline Trace

Model Pipeline - Model evaluation best practices

This pipeline shows how a computer vision model is trained and evaluated carefully to ensure it works well on new images. It includes data preparation, training, checking performance, and making predictions.

Data Flow - 6 Stages

1Raw image data

1000 images x 64x64 pixels x 3 color channels→Collect images with labels (e.g., cats, dogs)→1000 images x 64x64 pixels x 3 color channels

Image of a cat labeled 'cat'

↓

2Preprocessing

1000 images x 64x64 pixels x 3 color channels→Resize images, normalize pixel values (0-1)→1000 images x 64x64 pixels x 3 color channels

Normalized image pixels between 0 and 1

↓

3Train/test split

1000 images x 64x64 pixels x 3 color channels→Split data into 800 training and 200 testing images→Training: 800 images x 64x64 pixels x 3, Testing: 200 images x 64x64 pixels x 3

Training image of a dog, testing image of a cat

↓

4Model training

800 images x 64x64 pixels x 3→Train convolutional neural network to classify images→Trained model

Model learns to recognize features like edges and shapes

↓

5Model evaluation

200 images x 64x64 pixels x 3→Evaluate model on test images using accuracy, precision, recall→Performance metrics (accuracy, precision, recall)

Accuracy = 85%, Precision = 80%, Recall = 75%

↓

6Prediction

New image x 64x64 pixels x 3→Model predicts label for new image→Predicted label (e.g., 'cat')

Model predicts 'dog' for a new dog image

Training Trace - Epoch by Epoch

Loss
1.2 |*       
0.9 | *      
0.7 |  *     
0.5 |   *    
0.4 |    *   
    +---------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.50	Model starts learning, accuracy is low
2	0.9	0.65	Loss decreases, accuracy improves
3	0.7	0.75	Model learns important features
4	0.5	0.82	Good improvement, model generalizes better
5	0.4	0.85	Training converges, accuracy stabilizes

Prediction Trace - 6 Layers

Layer 1: Input layer

Layer 2: Convolutional layers

Layer 3: Pooling layers

Layer 4: Fully connected layers

Layer 5: Softmax activation

Layer 6: Prediction

Model Quiz - 3 Questions

Why do we split data into training and testing sets?

A To make the training faster

B To check if the model works well on new, unseen data

C To increase the size of the dataset

D To reduce the number of features

Key Insight

Evaluating a model properly means testing it on data it has never seen before. Watching loss go down and accuracy go up during training shows the model is learning. Using metrics like precision and recall helps understand strengths and weaknesses beyond just accuracy.

Practice

1. Why is it important to use a separate test set when evaluating a computer vision model?

easy

A. To check how well the model performs on new, unseen data

B. To make the training process faster

C. To increase the size of the training data

D. To reduce the number of model parameters

Solution

1. Step 1: Understand the purpose of a test set

   The test set is data the model has never seen before, used to check real-world performance.

2. Step 2: Compare test set role with other options

   Options B, C, and D do not relate to evaluation but to training or model design.

3. Final Answer:

   To check how well the model performs on new, unseen data -> Option A

4. Quick Check:

   Test set = unseen data check [OK]

Hint: Test set = new data to check model accuracy [OK]

Common Mistakes:

• Confusing test set with training set
• Thinking test set speeds up training
• Believing test set changes model size

2. Which of the following is the correct way to split data for model evaluation in Python using scikit-learn?

easy

A. split_train_test(data, 0.2)

B. train_test_split(data, test_size=0.2, random_state=42)

C. train_test(data, 0.2)

D. test_train_split(data, 0.2)

Solution

1. Step 1: Recall the correct function name in scikit-learn

   The function to split data is called train_test_split with parameters like test_size and random_state.

2. Step 2: Check the options for correct syntax

   Only train_test_split(data, test_size=0.2, random_state=42) uses the correct function name and parameters; others are invalid or do not exist.

3. Final Answer:

   train_test_split(data, test_size=0.2, random_state=42) -> Option B

4. Quick Check:

   Correct function = train_test_split [OK]

Hint: Remember scikit-learn function: train_test_split [OK]

Common Mistakes:

• Using wrong function names
• Missing required parameters
• Confusing order of train and test

3. Given the following code snippet, what will be the printed accuracy?

from sklearn.metrics import accuracy_score
true_labels = [1, 0, 1, 1, 0]
pred_labels = [1, 0, 0, 1, 0]
accuracy = accuracy_score(true_labels, pred_labels)
print("{:.2f}".format(round(accuracy, 2)))

medium

A. 0.60

B. 0.40

C. 0.80

D. 1.00

Solution

1. Step 1: Compare true and predicted labels

   True: [1, 0, 1, 1, 0], Predicted: [1, 0, 0, 1, 0]. Matches at positions 0,1,3,4 (4 correct out of 5).

2. Step 2: Calculate accuracy

   Accuracy = correct predictions / total = 4/5 = 0.8. Rounded to 2 decimals is 0.80.

3. Final Answer:

   0.80 -> Option C

4. Quick Check:

   Accuracy = 4/5 = 0.80 [OK]

Hint: Count matches, divide by total labels [OK]

Common Mistakes:

• Counting wrong matches
• Not rounding accuracy
• Confusing accuracy with precision

4. You trained a model but the test accuracy is much higher than the training accuracy. What is the most likely issue?

medium

A. Data leakage between training and test sets

B. Model is underfitting the training data

C. Test set is too small

D. Training data is too large

Solution

1. Step 1: Understand unusual accuracy pattern

   Test accuracy higher than training is unusual and often means test data was seen during training.

2. Step 2: Identify cause from options

   Data leakage means test data accidentally used in training, causing inflated test accuracy.

3. Final Answer:

   Data leakage between training and test sets -> Option A

4. Quick Check:

   High test accuracy > training = data leakage [OK]

Hint: High test accuracy than train? Check data leakage [OK]

Common Mistakes:

• Assuming underfitting causes higher test accuracy
• Ignoring data leakage possibility
• Blaming test set size without evidence

5. You want to evaluate a computer vision model for detecting rare objects in images. Which evaluation metric is best to use and why?

hard

A. Confusion matrix, because it shows training time

B. Accuracy, because it shows overall correct predictions

C. Mean Squared Error, because it measures prediction error

D. F1 score, because it balances precision and recall for imbalanced data

Solution

1. Step 1: Understand the problem of rare object detection

   Rare objects mean data is imbalanced; many negatives, few positives.

2. Step 2: Choose metric suitable for imbalanced data

   F1 score balances precision (correct positive predictions) and recall (finding all positives), ideal for rare classes.

3. Final Answer:

   F1 score, because it balances precision and recall for imbalanced data -> Option D

4. Quick Check:

   Rare class? Use F1 score [OK]

Hint: Rare classes? Use F1 score for balance [OK]

Common Mistakes:

• Using accuracy which hides imbalance
• Confusing regression metrics with classification
• Misunderstanding confusion matrix purpose