Create app.py

app.py

@@ -0,0 +1,86 @@
+import torch, torchvision
+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 resnet import ResNet18
+import gradio as gr
+
+model = ResNet18()
+model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False)
+
+inv_normalize = transforms.Normalize(
+    mean=[-0.50/0.23, -0.50/0.23, -0.50/0.23],
+    std=[1/0.23, 1/0.23, 1/0.23]
+)
+classes = ('plane', 'car', 'bird', 'cat', 'deer',
+           'dog', 'frog', 'horse', 'ship', 'truck')
+
+def resize_image_pil(image, new_width, new_height):
+
+    # Convert to PIL image
+    img = Image.fromarray(np.array(image))
+    
+    # Get original size
+    width, height = img.size
+
+    # Calculate scale
+    width_scale = new_width / width
+    height_scale = new_height / height 
+    scale = min(width_scale, height_scale)
+
+    # Resize
+    resized = img.resize((int(width*scale), int(height*scale)), Image.NEAREST)
+    
+    # Crop to exact size
+    resized = resized.crop((0, 0, new_width, new_height))
+
+    return resized
+
+def inference(input_img, transparency = 0.5, target_layer_number = -1):
+    input_img = resize_image_pil(input_img, 32, 32)
+    
+    input_img = np.array(input_img)
+    org_img = input_img
+    input_img = input_img.reshape((32, 32, 3))
+    transform = transforms.ToTensor()
+    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)
+    grayscale_cam = cam(input_tensor=input_img, targets=None)
+    grayscale_cam = grayscale_cam[0, :]
+    # img = input_img.squeeze(0)
+    # img = inv_normalize(img)
+    # print(transparency)
+    visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=transparency)
+    return classes[prediction[0].item()], visualization, confidences
+
+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(width=256, height=256, label="Input Image"), gr.Slider
+        (0, 1, value = 0.5, label="Overall Opacity of Image"), 
+        gr.Slider(-2, -1, value = -2, step=1, label="Which Layer?")
+        ], 
+    outputs = [
+        "text", 
+        gr.Image(width=256, height=256, label="Output"),
+        gr.Label(num_top_classes=3)
+        ],
+    title = title,
+    description = description,
+    examples = examples,
+)
+demo.launch()