evaluate.py

# evaluate.py
import torch
import torch.nn.functional as F
from sklearn.metrics import accuracy_score, precision_recall_fscore_support, confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
from train import model, testloader

def evaluate_model():
    model.eval()
    all_preds = []
    all_labels = []

    with torch.no_grad():
        for inputs, labels in testloader:
            outputs = model(inputs)
            _, predicted = torch.max(outputs, 1)
            all_preds.extend(predicted.numpy())
            all_labels.extend(labels.numpy())

    acc = accuracy_score(all_labels, all_preds)
    precision, recall, f1, _ = precision_recall_fscore_support(all_labels, all_preds, average='weighted')
    cm = confusion_matrix(all_labels, all_preds)

    print(f"Accuracy: {acc}")
    print(f"Precision: {precision}, Recall: {recall}, F1-Score: {f1}")

    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
    plt.show()

evaluate_model()