Update app.py

app.py

@@ -24,35 +24,40 @@ model = LitCifar().cpu()
 model.load_state_dict(torch.load('final_dict.pth', map_location=torch.device('cpu')))
 model.eval() 
 
-classes = ('plane', 'car', 'bird', 'cat',
-           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
-global_classes = 5
+classes = ('plane', 'car', 'bird', 'cat', 'deer',
+           'dog', 'frog', 'horse', 'ship', 'truck')
 
-def inference(input_image, transparency, target_layer, num_top_classes1, gradcam_image_display = False):
- image = input_image
- test_transform = TestAlbumentation()
- image1 = test_transform(image)
- image1 = image1.unsqueeze(0).cpu()
- out0 = model(image1)
- out = out0.detach().numpy()
- confidences = {classes[i] : float(out[0][i]) for i in range(10)}
- val = torch.argmax(out0).detach().numpy().tolist()
- target = [val]
- input_image_np,visualization=gradcame(model, 0, target, image1, target_layer, transparency)
- return confidences, visualization
- 
-interface = gr.Interface(inference, 
-                         inputs = [gr.Image(shape=(32,32), type="pil", label = "Input image"), 
-                         gr.Slider(0,1, value = 0.5, label="opacity"), 
-                         gr.Slider(-2,-1, value = -2, step = 1, label="gradcam layer"),
-                         gr.Slider(0,9, value = 0, step = 1, label="no. of top classes to display"), 
-                         gr.Checkbox(default=False, label="Show Gradcam Image")],
-                         outputs = [gr.Label(num_top_classes=global_classes),
-                         gr.Image(shape=(32,32), label = "Output")],
-                         title = "Gradcam output of network trained on cifar10",
-                         examples = [["cat.jpg", 0.5, -1], ["dog.jpg",0.5,-1]],
-                         )
+def inference(input_img, transparency = 0.5, target_layer_number = -1):
+    transform = transforms.ToTensor()
+    org_img = input_img
+    input_img = transform(input_img)
+    input_img = input_img
+    input_img = input_img.unsqueeze(0)
+    outputs = model(input_img)
+    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)
+    target_layers = [model.layer2[target_layer_number]]
+    cam = GradCAM(model=model, target_layers=target_layers, use_cuda=False)
+    grayscale_cam = cam(input_tensor=input_img, targets=None)
+    grayscale_cam = grayscale_cam[0, :]
+    img = input_img.squeeze(0)
+    img = inv_normalize(img)
+    rgb_img = np.transpose(img, (1, 2, 0))
+    rgb_img = rgb_img.numpy()
+    visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=transparency)
+    return confidences, visualization
 
-
-# Launch the Gradio interface
-interface.launch()
+title = "CIFAR10 trained on ResNet18 Model with GradCAM"
+description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results"
+examples = [["cat.jpg", 0.5, -1], ["dog.jpg", 0.5, -1]]
+demo = gr.Interface(
+    inference, 
+    inputs = [gr.Image(shape=(32, 32), label="Input Image"), gr.Slider(0, 1, value = 0.5, label="Opacity of GradCAM"), gr.Slider(-2, -1, value = -2, step=1, label="Which Layer?")], 
+    outputs = [gr.Label(num_top_classes=3), gr.Image(shape=(32, 32), label="Output").style(width=128, height=128)],
+    title = title,
+    description = description,
+    examples = examples,
+)
+demo.launch()