Added caching

app.py

@@ -27,6 +27,8 @@ test_loader = dataset.get_test_data_loader(**dataloader_args)
 classes = ('plane', 'car', 'bird', 'cat', 'deer',
            'dog', 'frog', 'horse', 'ship', 'truck')
 
+cache_dict = {"missclassified_images": None, "is_missclassified_images": None, "num_missclassified_images": None}
+
 def resize_image_pil(image, new_width, new_height):
 
     # Convert to PIL image
@@ -84,13 +86,20 @@ def inference(input_img, is_grad_cam=True, transparency = 0.5, target_layer_numb
     # Pick the top n predictions
     top_n_confidences = dict(list(sorted_confidences.items())[:top_predictions])
 
-    if is_missclassified_images:
-        # Get the misclassified data from test dataset
-        misclassified_data = get_misclassified_data(model, device, test_loader)
-        # Plot the misclassified data
-        missclassified_images = display_cifar_misclassified_data(misclassified_data, number_of_samples=num_missclassified_images)
+    if (is_missclassified_images != cache_dict["num_missclassified_images"] or
+         num_missclassified_images != cache_dict["num_missclassified_images"]):
+        cache_dict["num_missclassified_images"] = is_missclassified_images
+        cache_dict["num_missclassified_images"] = num_missclassified_images
+        if is_missclassified_images:
+            # Get the misclassified data from test dataset
+            misclassified_data = get_misclassified_data(model, device, test_loader)
+            # Plot the misclassified data
+            misclassified_images = display_cifar_misclassified_data(misclassified_data, number_of_samples=num_missclassified_images)
+            cache_dict["missclassified_images"] = misclassified_images
+        else:
+            missclassified_images = None
     else:
-        missclassified_images = None
+        missclassified_images = cache_dict["missclassified_images"]
     
     return classes[prediction[0].item()], visualization, top_n_confidences, missclassified_images