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.