1. def visualize_model(model, num_images=9):
2.     was_training = model.training
3.     model.eval()
4.     images_handeled = 0
5.     fig = plt.figure(figsize=(4, 4))  # Figür boyutunu ayarlayın
6.  
7.     with torch.no_grad():
8.         for i, (inputs, labels) in enumerate(testloader):
9.             inputs = inputs.to(device)
10.             labels = labels.to(device)
11.  
12.             outputs = model(inputs)
13.             _, preds = torch.max(outputs, 1)
14.  
15.             for j in range(inputs.size()[0]):
16.                 images_handeled += 1
17.                 ax = plt.subplot(3, 3, images_handeled)  # 3x3'lük bir gridde subplot oluşturun
18.                 ax.axis('off')
19.                 ax.set_title('Actual: {} Predicted: {}'.format(class_names[labels[j].item()],class_names[preds[j]]))
20.                 imshow(inputs.cpu().data[j])
21.  
22.                 if images_handeled == num_images:
23.                     model.train(mode=was_training)
24.                     return
25.         model.train(mode=was_training)
26.  
27. # Modelinizi ve görüntü sayısını belirtin
28. visualize_model(model, num_images=9)