Upload README.md with huggingface_hub

README.md

@@ -1,15 +1,12 @@
 ---
-license: mit
-tags:
-- deepfake-detection
-- computer-vision
-- transfer-learning
-- hybrid-cnn
-- pytorch
-datasets:
-- xhlulu/140k-real-and-fake-faces
-metrics:
-- accuracy
+title: Deepfake Detector
+emoji: 🔍
+colorFrom: purple
+colorTo: blue
+sdk: gradio
+sdk_version: "4.0.0"
+app_file: app.py
+pinned: false
 ---
 
 # Deepfake Face Detector
@@ -18,33 +15,10 @@ A hybrid CNN model for detecting AI-generated (deepfake) face images, built usin
 
 ## Model Architecture
 
-This model combines two parallel CNN streams:
-
-- **Spatial Stream** — EfficientNet-B4 pretrained on ImageNet, fine-tuned to detect visible artifacts such as unnatural skin texture, blending edges, and facial inconsistencies
-- **Frequency Stream** — Xception backbone with fixed SRM (Steganalysis Rich Model) filters to detect invisible GAN noise fingerprints in pixel residuals
-- **Fusion Module** — Both stream outputs are concatenated (1792 + 2048 = 3840 features) and passed through a classification head with Dropout regularization
-- **Output** — Sigmoid activation producing a probability score (0 = fake, 1 = real)
-
-## Training Strategy
-
-Three-phase transfer learning approach:
-
-| Phase | Layers Trained | Learning Rate | Epochs |
-|-------|---------------|---------------|--------|
-| 1 | Classifier head only | 1e-3 | 3 |
-| 2 | Top EfficientNet blocks + classifier | 1e-4 | 3 |
-
-## Dataset
-
-Trained and evaluated on [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces)
-
-| Split | Real | Fake | Total |
-|-------|------|------|-------|
-| Train | 50,000 | 50,000 | 100,000 |
-| Valid | 10,000 | 10,000 | 20,000 |
-| Test  | 10,000 | 10,000 | 20,000 |
-
-Fake images are StyleGAN2-generated faces. Real images are sourced from Flickr-Faces-HQ (FFHQ).
+- **Spatial Stream** — EfficientNet-B4 pretrained on ImageNet, detects visible artifacts
+- **Frequency Stream** — Xception + SRM filters, detects invisible GAN noise fingerprints
+- **Fusion Module** — Concatenates both streams (3840 features) into a classification head
+- **Output** — Sigmoid probability (0 = fake, 1 = real)
 
 ## Performance
 
@@ -53,38 +27,11 @@ Fake images are StyleGAN2-generated faces. Real images are sourced from Flickr-F
 | Test Accuracy | 98.59% |
 | Validation Accuracy | 98.55% |
 
-## Usage
-```python
-import torch
-from torchvision import transforms
-from PIL import Image
-
-model = HybridDeepfakeDetector()
-model.load_state_dict(torch.load("deepfake_detector_phase2.pth", map_location="cpu"))
-model.eval()
-
-transform = transforms.Compose([
-    transforms.Resize((224, 224)),
-    transforms.ToTensor(),
-    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-])
-
-image = Image.open("face.jpg").convert("RGB")
-tensor = transform(image).unsqueeze(0)
-
-with torch.no_grad():
-    prob = model(tensor).item()
+## Dataset
 
-label = "REAL" if prob > 0.5 else "FAKE"
-print(f"{label} ({prob*100:.1f}% confidence)")
-```
+Trained on [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) — 100k training images, balanced real/fake split.
 
 ## Limitations
-
-- Optimized for StyleGAN2 generated faces — may perform differently on other GAN architectures
+- Optimized for StyleGAN2 generated faces
 - Best results on frontal face images
 - Not tested on video deepfakes
-
-## Try It
-
-Live demo available at [Hugging Face Spaces](https://huggingface.co/spaces/AdityaManojShinde/deepfake-detector-app)