Create app.py

app.py

@@ -0,0 +1,96 @@
+import torch
+from torchvision import transforms
+import numpy as np
+import gradio as gr
+from PIL import Image
+from pytorch_grad_cam import GradCAM
+from pytorch_grad_cam.utils.image import show_cam_on_image
+from custom_resnet import *
+#from resnet import ResNet18  # Assuming you have a custom ResNet18 implementation
+
+def load_custom_state_dict(model, state_dict):
+    model_state_dict = model.state_dict()
+    # Filter out unexpected keys
+    filtered_state_dict = {k: v for k, v in state_dict.items() if k in model_state_dict}
+    # Update the model's state_dict
+    model_state_dict.update(filtered_state_dict)
+    # Load the updated state_dict to the model
+    model.load_state_dict(model_state_dict)
+
+    
+model = CustomResNet()  # Replace this with your CustomResNet if necessary
+# Load the state_dict using the custom function
+state_dict = torch.load("model_pth.ckpt", map_location=torch.device('cpu'))
+load_custom_state_dict(model, state_dict['state_dict'])
+
+inv_normalize = transforms.Normalize(
+    mean=[-0.494 / 0.2470, -0.4822 / 0.2435, -0.4465 / 0.2616],
+    std=[1 / 0.2470, 1 / 0.2435, 1 / 0.2616]
+)
+classes = ('plane', 'car', 'bird', 'cat', 'deer',
+           'dog', 'frog', 'horse', 'ship', 'truck')
+
+def inference(input_img, transparency=0.5, target_layer_number=-1, num_images=1, num_top_classes=3):
+    transform = transforms.ToTensor()
+    org_img = input_img
+    input_img = transform(input_img)
+    input_img = input_img.unsqueeze(0)
+    outputs = model(input_img)
+    softmax = torch.nn.Softmax(dim=1)
+    probabilities = softmax(outputs)
+    confidences = {classes[i]: float(probabilities[0, i]) for i in range(10)}
+
+    _, prediction = torch.max(outputs, 1)
+
+    # Get GradCAM for the specified target_layer_number
+    target_layers = [model.layer_2[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()
+
+    # Convert org_img (PIL image) to a NumPy array before performing arithmetic operations
+    visualization = show_cam_on_image(org_img / 255, grayscale_cam, use_rgb=True, image_weight=transparency)
+
+    # Create a list to store multiple visualizations
+
+
+    # # Generate multiple GradCAM visualizations if num_images > 1
+    # for _ in range(num_images - 1):
+    #     # Get GradCAM for different target_layer_number if provided by the user
+    #     if target_layer_number >= -1:
+    #         target_layers = [model.layer_2[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, :]
+
+    #     visualization = show_cam_on_image(org_img / 255, grayscale_cam, use_rgb=True, image_weight=transparency)
+    #     visualizations.append(visualization)
+
+    # Get top classes based on user input (up to a maximum of 10)
+    top_classes = {k: v for k, v in sorted(confidences.items(), key=lambda item: item[1], reverse=True)[:min(num_top_classes, 10)]}
+
+    return top_classes, visualization
+
+
+
+
+title = "CIFAR10 trained on ResNet18 Model with GradCAM"
+description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results"
+examples = [["/content/examples/car_1.jpg",0.5,-1],["/content/examples/car_2.jpg",0.5,-1],["/content/examples/cat_1.jpg",0.5,-1],["/content/examples/cat_2.jpg",0.5,-1],["/content/examples/dog_1.jpg",0.5,-1],["/content/examples/dog_2.jpg",0.5,-1],["/content/examples/frog_1.jpg",0.5,-1],["/content/examples/frog_2.jpg",0.5,-1],["/content/examples/horse_1.jpg",0.5,-1],["/content/examples/horse_2.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?"),
+              gr.Number(default=1, label="Number of GradCAM Images to Show"),
+              gr.Slider(1, 10, value=3, step=1, label="Number of Top Classes to Show")],
+    outputs = [gr.Label(num_top_classes=5), gr.Image(shape=(32, 32), label="Output").style(width=128, height=128)],
+    title = title,
+    description = description,
+    examples = examples,
+)
+demo.launch()