Spaces:

TruthLens
/

fake-real

Runtime error

App Files Files Community

TruthLens commited on Feb 22

Commit

e064416

verified ·

1 Parent(s): 3a9179e

Update app.py

Browse files

Files changed (1) hide show

app.py +56 -65

app.py CHANGED Viewed

@@ -3,7 +3,7 @@ from flask import Flask, request, render_template_string
 from PIL import Image
 import torch
 from torchvision import models, transforms
-import requests
 app = Flask(__name__)
@@ -11,18 +11,19 @@ app = Flask(__name__)
 upload_folder = os.path.join('static', 'uploads')
 os.makedirs(upload_folder, exist_ok=True)
-# Download ImageNet class labels
-imagenet_class_labels_url = 'https://raw.githubusercontent.com/anishathalye/imagenet-simple-labels/master/imagenet-simple-labels.json'
-response = requests.get(imagenet_class_labels_url)
-imagenet_class_labels = response.json()
-# Load pre-trained ResNet50 for object classification
-resnet50_model = models.resnet50(weights=models.ResNet50_Weights.DEFAULT)
-resnet50_model.eval()
-# Load ResNet18 for AI vs. Human detection (Use custom-trained weights if available)
-resnet18_model = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)
-resnet18_model.eval()
 # Image transformation pipeline
 transform = transforms.Compose([
@@ -31,60 +32,52 @@ transform = transforms.Compose([
     transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
 ])
-# HTML Template with improved UI and interpretation
 HTML_TEMPLATE = """
 <!DOCTYPE html>
 <html lang="en">
 <head>
     <meta charset="UTF-8">
-    <title>AI & Image Detection</title>
     <style>
         body { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; background-color: #f5f5f5; padding: 20px; }
-        .container { background: white; padding: 30px; border-radius: 12px; max-width: 750px; margin: auto; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1); }
-        h1, h2 { color: #333; }
-        textarea, input[type="file"] { width: 100%; padding: 12px; margin-top: 10px; border-radius: 8px; border: 1px solid #ccc; }
-        button { background-color: #4CAF50; color: white; border: none; padding: 12px 20px; border-radius: 8px; cursor: pointer; font-size: 16px; }
         button:hover { background-color: #45a049; }
         .result { background: #e7f3fe; padding: 15px; border-radius: 10px; margin-top: 20px; }
-        ul { text-align: left; }
     </style>
 </head>
 <body>
     <div class="container">
-        <h1>📰 Fake News & Image Detection</h1>
         <form method="POST" action="/detect">
             <textarea name="text" placeholder="Enter news text..." required></textarea>
             <button type="submit">Detect News Authenticity</button>
         </form>
-        <h1>🖼️ Upload Image for Detection</h1>
-        <form method="POST" action="/detect_image" enctype="multipart/form-data">
-            <input type="file" name="image" required>
-            <button type="submit">Upload and Analyze</button>
-        </form>
-        <div style="margin-top: 30px;">
-            <h2>🤖 What is ResNet50?</h2>
-            <p>ResNet50 is a 50-layer deep convolutional neural network designed for image classification tasks. It can recognize thousands of objects from the ImageNet dataset.</p>
-        </div>
-        {% if ai_prediction %}
         <div class="result">
-            <h2>🧠 AI vs. Human Detection Result:</h2>
-            <p>{{ ai_prediction }}</p>
-            <p><strong>Interpretation:</strong> This result indicates whether the uploaded image was likely created by AI or a human. Higher confidence suggests stronger model certainty.</p>
         </div>
         {% endif %}
-        {% if classification_results %}
         <div class="result">
-            <h2>📦 Object Classification Results (ResNet50):</h2>
-            <ul>
-                {% for result in classification_results %}
-                <li>• {{ result.label }} ({{ (result.score * 100) | round(2) }}%) - Detected object category.</li>
-                {% endfor %}
-            </ul>
-            <p><strong>Interpretation:</strong> The model predicts the most probable object categories in the uploaded image along with confidence scores. Higher percentages indicate stronger matches.</p>
         </div>
         {% endif %}
     </div>
@@ -99,41 +92,39 @@ def home():
 @app.route("/detect", methods=["POST"])
 def detect():
     text = request.form.get("text")
-    final_label = "REAL" if "trusted" in text.lower() else "FAKE"  # Placeholder logic
-    return render_template_string(HTML_TEMPLATE, ai_prediction=f"News is {final_label}.", classification_results=None)
 @app.route("/detect_image", methods=["POST"])
 def detect_image():
     if "image" not in request.files:
-        return "No image uploaded.", 400
     file = request.files["image"]
-    img_path = os.path.join(upload_folder, file.filename)
-    file.save(img_path)
-    img = Image.open(img_path).convert("RGB")
-    img_tensor = transform(img).unsqueeze(0)
-    # AI vs. Human detection
     with torch.no_grad():
-        ai_output = resnet18_model(img_tensor)
-        ai_confidence = torch.softmax(ai_output, dim=1).max().item()
-        ai_label = "AI-Generated" if ai_confidence > 0.55 else "Human-Created"
-    # Object classification with ResNet50
-    with torch.no_grad():
-        outputs = resnet50_model(img_tensor)
-        probs = torch.softmax(outputs, dim=1)[0]
-        top5_probs, top5_indices = torch.topk(probs, 5)
-        classification_results = [
-            {"label": imagenet_class_labels[idx], "score": prob.item()} for idx, prob in zip(top5_indices, top5_probs)
-        ]
     return render_template_string(
         HTML_TEMPLATE,
-        ai_prediction=f"{ai_label} (Confidence: {(ai_confidence * 100):.2f}%)",
-        classification_results=classification_results
     )
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860)  # Updated for Hugging Face Spaces (no ngrok required)

 from PIL import Image
 import torch
 from torchvision import models, transforms
+from transformers import pipeline, CLIPProcessor, CLIPModel
 app = Flask(__name__)
 upload_folder = os.path.join('static', 'uploads')
 os.makedirs(upload_folder, exist_ok=True)
+# Load Updated Fake News Detection Pipelines
+news_models = {
+    "newsverify": pipeline("text-classification", model="newsverify/roberta-fake-news"),
+    "fakenewsdetector": pipeline("text-classification", model="fakenewsdetector/bert-fake-news")
+}
+# Load Image Models for AI vs. Human Detection
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
+ai_image_models = {
+    "openai": clip_model
+}
 # Image transformation pipeline
 transform = transforms.Compose([
     transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
 ])
+# HTML Template with Model Selection
 HTML_TEMPLATE = """
 <!DOCTYPE html>
 <html lang="en">
 <head>
     <meta charset="UTF-8">
+    <title>AI & News Detection</title>
     <style>
         body { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; background-color: #f5f5f5; padding: 20px; }
+        .container { background: white; padding: 30px; border-radius: 12px; max-width: 800px; margin: auto; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1); }
+        textarea, select { width: 100%; padding: 12px; margin-top: 10px; border-radius: 8px; border: 1px solid #ccc; }
+        button { background-color: #4CAF50; color: white; border: none; padding: 12px 20px; border-radius: 8px; cursor: pointer; font-size: 16px; margin-top: 10px; }
         button:hover { background-color: #45a049; }
         .result { background: #e7f3fe; padding: 15px; border-radius: 10px; margin-top: 20px; }
     </style>
 </head>
 <body>
     <div class="container">
+        <h1>📰 Fake News Detection</h1>
         <form method="POST" action="/detect">
             <textarea name="text" placeholder="Enter news text..." required></textarea>
+            <label for="model">Select Fake News Model:</label>
+            <select name="model" required>
+                <option value="newsverify">NewsVerify (RoBERTa)</option>
+                <option value="fakenewsdetector">FakeNewsDetector (BERT)</option>
+            </select>
             <button type="submit">Detect News Authenticity</button>
         </form>
+        {% if news_prediction %}
         <div class="result">
+            <h2>🧠 News Detection Result:</h2>
+            <p>{{ news_prediction }}</p>
         </div>
         {% endif %}
+        <h1>🖼️ AI vs. Human Image Detection</h1>
+        <form method="POST" action="/detect_image" enctype="multipart/form-data">
+            <input type="file" name="image" required>
+            <button type="submit">Upload and Detect</button>
+        </form>
+        {% if image_prediction %}
         <div class="result">
+            <h2>📷 Image Detection Result:</h2>
+            <p>{{ image_prediction }}</p>
         </div>
         {% endif %}
     </div>
 @app.route("/detect", methods=["POST"])
 def detect():
     text = request.form.get("text")
+    model_key = request.form.get("model")
+    if not text or model_key not in news_models:
+        return render_template_string(HTML_TEMPLATE, news_prediction="Invalid input or model selection.")
+    result = news_models[model_key](text)[0]
+    label = "REAL" if result['label'].lower() in ["real", "label_1"] else "FAKE"
+    confidence = result['score'] * 100
+    return render_template_string(
+        HTML_TEMPLATE,
+        news_prediction=f"News is {label} (Confidence: {confidence:.2f}%)"
+    )
 @app.route("/detect_image", methods=["POST"])
 def detect_image():
     if "image" not in request.files:
+        return render_template_string(HTML_TEMPLATE, image_prediction="No image uploaded.")
     file = request.files["image"]
+    img = Image.open(file).convert("RGB")
+    inputs = clip_processor(images=img, return_tensors="pt")
     with torch.no_grad():
+        image_features = ai_image_models["openai"].get_image_features(**inputs)
+    prediction = "AI-Generated" if torch.mean(image_features).item() > 0 else "Human-Created"
     return render_template_string(
         HTML_TEMPLATE,
+        image_prediction=f"Prediction: {prediction}"
     )
 if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)  # Suitable for Hugging Face Spaces