Create app.py

app.py

@@ -0,0 +1,58 @@
+# app.py
+
+# Import necessary libraries
+import torch
+from PIL import Image
+from torchvision import transforms
+import gradio as gr
+import os
+
+# Download the labels file if not present
+os.system("wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt")
+
+# Load ResNet model
+model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet18', pretrained=True).eval()
+
+# Function for model inference
+def inference(input_image):
+    try:
+        # Preprocess the input image
+        preprocess = transforms.Compose([
+            transforms.Resize(256),
+            transforms.CenterCrop(224),
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        ])
+
+        input_tensor = preprocess(input_image)
+        input_batch = input_tensor.unsqueeze(0)  # Create a mini-batch as expected by the model
+
+        # Move the input and model to GPU for speed if available
+        if torch.cuda.is_available():
+            input_batch = input_batch.to('cuda')
+            model.to('cuda')
+
+        with torch.no_grad():
+            output = model(input_batch)
+
+        # The output has unnormalized scores. To get probabilities, run a softmax on it.
+        probabilities = torch.nn.functional.softmax(output[0], dim=0)
+
+        # Read the categories from the labels file
+        with open("imagenet_classes.txt", "r") as f:
+            categories = [s.strip() for s in f.readlines()]
+
+        # Show top categories per image
+        top5_prob, top5_catid = torch.topk(probabilities, 5)
+        result = {categories[top5_catid[i]]: top5_prob[i].item() for i in range(top5_prob.size(0))}
+
+        return result
+    except Exception as e:
+        return {"error": str(e)}
+
+# Gradio Interface setup
+inputs = gr.Image(type='pil', label="Upload Image")
+outputs = gr.Label(num_top_classes=5, label="Predictions")  # Removed 'type' parameter
+
+# Launch Gradio Interface
+gr.Interface(inference, inputs, outputs, title="ResNet Image Classifier", description="Classify images using ResNet", analytics_enabled=False).launch()