add app.py

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import torchvision
+from torchvision.transforms import transforms
+import torch
+import requests
+
+# Demo for image classification
+model = torchvision.models.resnet18(pretrained=True)
+
+trans_seq = torchvision.transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+model.eval()
+
+# Download human-readable labels for ImageNet.
+response = requests.get("https://git.io/JJkYN")
+labels = response.text.split("\n")
+
+                                                  
+def predict(image):
+    """
+    Predicts the confidences of different labels for the given image.
+
+    Args:
+        image (torch.Tensor): The input image tensor.
+
+    Returns:
+        dict: A dictionary containing the label names as keys and their corresponding confidences as values.
+    """
+    image = trans_seq(image)
+    image = image.unsqueeze(0)
+    with torch.no_grad():
+        prediction = torch.nn.functional.softmax(model(image)[0], dim=0)
+        confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
+    return confidences
+
+# Pull out some examples from internet images
+examples =[
+    "https://github.com/EliSchwartz/imagenet-sample-images/raw/master/n01484850_great_white_shark.JPEG", 
+    "https://github.com/EliSchwartz/imagenet-sample-images/raw/master/n01443537_goldfish.JPEG",
+    "https://github.com/EliSchwartz/imagenet-sample-images/raw/master/n01632777_axolotl.JPEG",
+    "https://github.com/EliSchwartz/imagenet-sample-images/raw/master/n01534433_junco.JPEG",
+    "https://github.com/EliSchwartz/imagenet-sample-images/raw/master/n01753488_horned_viper.JPEG",
+           ]
+with gr.Blocks(theme="soft") as demo:
+    input_img = gr.Image(label="Input Image", type="pil")
+    output = gr.Label(num_top_classes=3)
+    exam = gr.Examples(examples=examples, examples_per_page=10, inputs=[input_img], outputs=[output])
+    input_img.change(predict, inputs=[input_img], outputs=[output])
+    
+demo.launch()