Upload DeepSVDD model with all files

README.md

@@ -0,0 +1,54 @@
+# One-Class Deepfake Detector
+
+## Model Details
+- **Architecture**: Hybrid CNN + ViT + FFT Frequency Features
+- **Training Images**: 50,000 real images only
+- **Final Radius**: 352.6608
+- **Final Loss**: 124397.0862
+- **Embedding Dim**: 512
+
+## How It Works
+This is a **one-class anomaly detector** using DeepSVDD (Deep Support Vector Data Description).
+It learns a "hypersphere" around real images in embedding space. Images far from this 
+hypersphere are considered anomalous (fake).
+
+## Usage
+```python
+import torch
+from PIL import Image
+import torchvision.transforms as transforms
+
+# Load model
+model_data = torch.load('deepfake_detector_model/deepsvdd_model.pth')
+# Initialize your model and load weights
+# model.load_state_dict(model_data['model_state_dict'])
+
+# Preprocess image
+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('test.jpg').convert('RGB')
+image_tensor = transform(image).unsqueeze(0)
+
+# Get hypersphere distance
+with torch.no_grad():
+    embedding = model(image_tensor)
+    distance = model.get_distance(embedding).item()
+
+# Compare to threshold
+threshold = model_data['radius'].item() * 1.5
+is_fake = distance > threshold
+
+print(f"Distance: {distance:.4f}, Threshold: {threshold:.4f}, Fake: {is_fake}")
+```
+
+## Files
+- `deepsvdd_model.pth`: Complete model with center and radius
+- `encoder.pth`: Encoder weights only
+- `config.json`: Training configuration
+- `training_history.json`: Training metrics
+
+Generated: 2025-11-28 11:22:17

config.json

@@ -0,0 +1 @@
+{}

deepsvdd_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a373cb03333bc6a5f9563f3198da71a9fb426b82af08611f6fd1c2adf5e723
+size 520423822

encoder.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a11f14833871d95b836aa38da0a2a260ff7002e20c4ad27a42c65276602357
+size 520414401

training_history.json

@@ -0,0 +1,62 @@
+{
+  "epoch": [
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10
+  ],
+  "loss": [
+    130806.78340068822,
+    128270.91292213509,
+    127369.4989696703,
+    126559.78205025608,
+    125866.87391965429,
+    125308.6836487676,
+    124897.57395366517,
+    124622.66649327785,
+    124464.91485275287,
+    124397.08623759603
+  ],
+  "mean_distance": [
+    128967.15688020167,
+    128096.77782890525,
+    127231.54814540653,
+    126447.16445262484,
+    125772.19833346672,
+    125230.22033050576,
+    124828.60117237516,
+    124560.093649968,
+    124408.1298515525,
+    124341.8554837548
+  ],
+  "radius": [
+    358.715576171875,
+    357.4587097167969,
+    356.2117004394531,
+    355.15203857421875,
+    354.3314514160156,
+    353.5955505371094,
+    353.140869140625,
+    352.86822509765625,
+    352.7275085449219,
+    352.66082763671875
+  ],
+  "lr": [
+    0.0001,
+    9.757729755661011e-05,
+    9.05463412215599e-05,
+    7.959536998847742e-05,
+    6.57963412215599e-05,
+    5.05e-05,
+    3.5203658778440106e-05,
+    2.1404630011522586e-05,
+    1.0453658778440107e-05,
+    3.4227024433899e-06
+  ]
+}