add app&examples

app.py

@@ -1,7 +1,36 @@
 import gradio as gr
+from PIL import Image
+import numpy as np
+import torch
+import torchvision
+from torchvision import transforms
 
-def greet(name):
-    return "Hello " + name + "!!"
+def predict_image(image):
+        image = image.convert('RGB')
+        test_transforms = transforms.Compose([
+                transforms.Resize([224, 224]),
+                transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+                ])
+        classes = ('Speed limit (20km/h)',
+                'Speed limit (30km/h)', 
+                'Speed limit (50km/h)', 
+                'Speed limit (60km/h)', 
+                'Speed limit (70km/h)', 
+                'Speed limit (80km/h)', 
+                'Speed limit (100km/h)', 
+                'Speed limit (120km/h)')
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        model = torch.load('vgg11.pt')
+        model.eval()
+        image_tensor = test_transforms(image).float()
+        image_tensor = image_tensor.unsqueeze_(0)
+        input = image_tensor.to(device)
+        output = model(input)
+        probs = torch.exp(output.data.cpu().squeeze()).numpy()
+        return dict(zip(classes, map(float, probs)))
+image = gr.Image(type='pil')
+label = gr.Label()
+examples = ['1.png', '2.png', '3.png']
+intf = gr.Interface(fn=predict_image, inputs=image, outputs=label, examples=examples)
+intf.launch(inline=True)