Model Evaluation

Step 9.1: Plot Training Curves

• Metrics Visualization: Plot the training and validation loss, binary accuracy, and subtype accuracy over epochs.

  • Purpose: Helps visualize the model's learning progress and identify overfitting or underfitting.

  

Step 9.2: Evaluate on Test Set

• Evaluation Function: evaluate_model() to assess the performance on the test dataset.

  • Metrics: Classification report and confusion matrix for both binary and subtype classification.
  • Purpose: Provides detailed insights into model performance across different classes.

  

Step 9.3: Display Predictions

• Display Predictions: Visualize predictions along with actual labels on the test set.

  • Function: show_predictions() to display a few samples with predictions.

  • Purpose: Verify how well the model performs on unseen data.