Upload 3 files

app.py

@@ -0,0 +1,122 @@
+import gradio as gr
+import torch
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+from PIL import Image
+import numpy as np
+
+# Load a logo recognition model from Hugging Face
+# Using a model fine-tuned for logo detection
+model_name = "google/mobilenet_v2_1.0_224"  # Fallback general purpose model
+processor_name = "google/mobilenet_v2_1.0_224"
+
+try:
+    # Try to load a specialized logo model if available
+    # Alternative: "facebook/dino-vits16" for better image understanding
+    image_processor = AutoImageProcessor.from_pretrained(processor_name)
+    model = AutoModelForImageClassification.from_pretrained(model_name)
+except Exception as e:
+    print(f"Error loading model: {e}")
+    image_processor = AutoImageProcessor.from_pretrained("google/mobilenet_v2_1.0_224")
+    model = AutoModelForImageClassification.from_pretrained("google/mobilenet_v2_1.0_224")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+model.eval()
+
+def recognize_logo(image):
+    """
+    Recognize a logo from an uploaded image.
+    
+    Args:
+        image: PIL Image object or numpy array
+        
+    Returns:
+        Dictionary with predictions and confidence scores
+    """
+    if image is None:
+        return "Please upload an image first."
+    
+    try:
+        # Convert to PIL Image if necessary
+        if isinstance(image, np.ndarray):
+            image = Image.fromarray(image)
+        elif not isinstance(image, Image.Image):
+            image = Image.fromarray(image)
+        
+        # Process the image
+        inputs = image_processor(images=image, return_tensors="pt").to(device)
+        
+        # Get predictions
+        with torch.no_grad():
+            outputs = model(**inputs)
+        
+        # Get logits and convert to probabilities
+        logits = outputs.logits
+        probabilities = torch.nn.functional.softmax(logits, dim=-1)
+        
+        # Get top predictions
+        top_k = 5
+        top_probs, top_indices = torch.topk(probabilities, top_k)
+        
+        # Format results
+        results = {}
+        for i, (prob, idx) in enumerate(zip(top_probs[0], top_indices[0])):
+            class_name = model.config.id2label.get(idx.item(), f"Class {idx.item()}")
+            confidence = float(prob.item()) * 100
+            results[class_name] = f"{confidence:.2f}%"
+        
+        return results
+    
+    except Exception as e:
+        return f"Error processing image: {str(e)}"
+
+# Create Gradio interface
+def create_interface():
+    with gr.Blocks(title="Logo Recognition AI") as demo:
+        gr.Markdown("""
+        # 🎯 Logo Recognition AI
+        
+        Upload a logo image and let our AI identify it!
+        
+        This application uses state-of-the-art image recognition models from Hugging Face
+        to analyze and identify logos from your images.
+        """)
+        
+        with gr.Row():
+            with gr.Column():
+                gr.Markdown("### Upload Your Logo")
+                image_input = gr.Image(
+                    type="pil",
+                    label="Logo Image",
+                    show_label=True,
+                    sources=["upload", "webcam"],
+                    interactive=True
+                )
+                submit_btn = gr.Button("🔍 Recognize Logo", variant="primary", size="lg")
+            
+            with gr.Column():
+                gr.Markdown("### Recognition Results")
+                output = gr.JSON(label="Predictions")
+        
+        submit_btn.click(
+            fn=recognize_logo,
+            inputs=image_input,
+            outputs=output
+        )
+        
+        # Add examples
+        gr.Markdown("### Example Logos")
+        gr.Markdown("""
+        Try uploading images of well-known logos such as:
+        - 🍎 Apple
+        - Ⓜ️ Microsoft
+        - 🅶 Google
+        - 📘 Facebook
+        - 🐦 Twitter
+        """)
+    
+    return demo
+
+if __name__ == "__main__":
+    interface = create_interface()
+    interface.launch(share=False)

models_config.py

@@ -0,0 +1,46 @@
+"""
+Advanced Logo Recognition Model Configuration
+This module provides different model options for logo recognition
+"""
+
+MODELS = {
+    "mobile_net": {
+        "name": "google/mobilenet_v2_1.0_224",
+        "processor": "google/mobilenet_v2_1.0_224",
+        "description": "Fast, lightweight model - Best for CPU",
+        "input_size": 224
+    },
+    "vit_base": {
+        "name": "google/vit-base-patch16-224",
+        "processor": "google/vit-base-patch16-224",
+        "description": "Vision Transformer - Better accuracy",
+        "input_size": 224
+    },
+    "resnet": {
+        "name": "microsoft/resnet-50",
+        "processor": "microsoft/resnet-50",
+        "description": "ResNet-50 - Good balance of speed/accuracy",
+        "input_size": 224
+    },
+    "dino": {
+        "name": "facebook/dino-vits16",
+        "processor": "facebook/dino-vits16",
+        "description": "DINO ViT - Excellent for visual understanding",
+        "input_size": 224
+    }
+}
+
+# Default model
+DEFAULT_MODEL = "mobile_net"
+
+# Model-specific configurations
+MODEL_CONFIG = {
+    "google/mobilenet_v2_1.0_224": {
+        "max_image_size": 2048,
+        "batch_size": 8
+    },
+    "google/vit-base-patch16-224": {
+        "max_image_size": 2048,
+        "batch_size": 4
+    }
+}

requirements.txt

@@ -0,0 +1,7 @@
+gradio==4.26.0
+torch==2.1.2
+torchvision==0.16.2
+transformers==4.36.2
+Pillow==10.1.0
+numpy==1.24.3
+huggingface-hub==0.20.3