Update app.py

app.py

@@ -19,7 +19,7 @@ classes = ('plane', 'car', 'bird', 'cat', 'deer',
 model = LITResNet(classes)
 model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False)
 
-def inference(input_img, input_img_label, show_gradcam, num_gradcam, layer_num, opacity, show_misclassified, num_misclassified, num_top_classes):
+def inference(input_img, num_gradcam_images=1, target_layer_number=-1, transparency=0.5, show_misclassified=False, num_top_classes=3):
     input_img = np.array(Image.fromarray(np.array(input_img)).resize((32,32)))
     org_img = input_img
 
@@ -30,60 +30,52 @@ def inference(input_img, input_img_label, show_gradcam, num_gradcam, layer_num,
     softmax = torch.nn.Softmax(dim=0)
     o = softmax(outputs.flatten())
     confidences = {classes[i]: float(o[i]) for i in range(10)}
-
     _, prediction = torch.max(outputs, 1)
-    is_misclassified = (prediction != classes.index(input_img_label))
 
-    if show_gradcam:
-        target_layers = [model.layer2[layer_num]]
+    if not show_misclassified or prediction[0].item() == np.argmax(list(confidences.values())):
+        target_layers = [model.layer2[target_layer_number]]
         cam = GradCAM(model=model, target_layers=target_layers)
         grayscale_cam = cam(input_tensor=input_img, targets=None)
         grayscale_cam = grayscale_cam[0, :]
+
         img = input_img.squeeze(0)
         img = inv_normalize(img)
-        visualization = [show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=opacity) for _ in range(num_gradcam)]
-    else:
-        visualization = []
 
-    if show_misclassified:
-        misclassified_imgs = [input_img for _ in range(num_misclassified)]
-    else:
-        misclassified_imgs = []
+        visualizations = []
+        for _ in range(num_gradcam_images):
+            visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=transparency)
+            visualizations.append(visualization)
 
-    sorted_confidences = dict(sorted(confidences.items(), key=lambda item: item[1], reverse=True)[:num_top_classes])
+        top_classes = sorted(confidences.items(), key=lambda x: x[1], reverse=True)[:num_top_classes]
+        top_classes = [f"{cls}: {conf:.2f}" for cls, conf in top_classes]
 
-    return prediction[0].item(), classes[prediction[0].item()], is_misclassified, sorted_confidences, visualization, misclassified_imgs
+        return prediction[0].item(), visualizations, top_classes
+    else:
+        return None, None, None
 
 title = "CIFAR10 trained on ResNet18 Model with GradCAM"
-description = "A simple Gradio interface to infer on ResNet model, get GradCAM results, and view misclassified images"
+description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results"
 
 examples = [
-    ["plane.jpeg", "plane", True, 1, -1, 0.5, False, 0, 3],
-    ["car.jpeg", "car", True, 2, -2, 0.7, True, 1, 5],
-    ["bird.jpeg", "bird", False, 0, -1, 0.5, False, 0, 3],
-    # Add more examples as needed
+    ["cat.jpg", 1, -1, 0.5, False, 3],
+    ["dog.jpg", 1, -1, 0.5, False, 3],
+    # Add more example images here
 ]
 
 demo = gr.Interface(
     inference,
     inputs=[
         gr.Image(width=256, height=256, label="Input Image"),
-        gr.Dropdown(choices=classes, label="Ground Truth Label"),
-        gr.Checkbox(value=True, label="Show GradCAM"),
         gr.Slider(1, 5, value=1, step=1, label="Number of GradCAM Images"),
         gr.Slider(-2, -1, value=-2, step=1, label="Which Layer?"),
         gr.Slider(0, 1, value=0.5, label="Overall Opacity of Image"),
-        gr.Checkbox(value=False, label="Show Misclassified Images"),
-        gr.Slider(1, 5, value=1, step=1, label="Number of Misclassified Images"),
-        gr.Slider(1, 10, value=3, step=1, label="Number of Top Classes to Show")
+        gr.Checkbox(label="Show Misclassified Images"),
+        gr.Slider(1, 10, value=3, step=1, label="Number of Top Classes")
     ],
     outputs=[
         "text",
-        "text",
-        "text",
-        gr.Label(num_top_classes=10),
-        gr.Gallery(label="GradCAM Visualizations"),
-        gr.Gallery(label="Misclassified Images")
+        gr.Gallery(label="GradCAM Images"),
+        gr.Label(num_top_classes=3, label="Top Classes")
     ],
     title=title,
     description=description,