Update README.md
Browse files
README.md
CHANGED
@@ -15,9 +15,18 @@ base_model:
|
|
15 |
# **Deep-Fake-Detector-Model**
|
16 |
|
17 |
# **Overview**
|
|
|
18 |
The **Deep-Fake-Detector-Model** is a state-of-the-art deep learning model designed to detect deepfake images. It leverages the **Vision Transformer (ViT)** architecture, specifically the `google/vit-base-patch16-224-in21k` model, fine-tuned on a dataset of real and deepfake images. The model is trained to classify images as either "Real" or "Fake" with high accuracy, making it a powerful tool for detecting manipulated media.
|
19 |
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
- **Architecture**: Vision Transformer (ViT) - `google/vit-base-patch16-224-in21k`.
|
22 |
- **Input**: RGB images resized to 224x224 pixels.
|
23 |
- **Output**: Binary classification ("Real" or "Fake").
|
|
|
15 |
# **Deep-Fake-Detector-Model**
|
16 |
|
17 |
# **Overview**
|
18 |
+
|
19 |
The **Deep-Fake-Detector-Model** is a state-of-the-art deep learning model designed to detect deepfake images. It leverages the **Vision Transformer (ViT)** architecture, specifically the `google/vit-base-patch16-224-in21k` model, fine-tuned on a dataset of real and deepfake images. The model is trained to classify images as either "Real" or "Fake" with high accuracy, making it a powerful tool for detecting manipulated media.
|
20 |
|
21 |
+
*Update* : The previous model checkpoint was obtained using a smaller classification dataset. Although it performed well in evaluation scores, its real-time performance was average due to limited variations in the training set. The new update includes a larger dataset to improve the detection of fake images.
|
22 |
+
|
23 |
+
*Repository Details*
|
24 |
+
|
25 |
+
| Repository | Link |
|
26 |
+
|------------|------|
|
27 |
+
| Deep Fake Detector Model | [GitHub Repository](https://github.com/PRITHIVSAKTHIUR/Deep-Fake-Detector-Model) |
|
28 |
+
|
29 |
+
# **Key Features**
|
30 |
- **Architecture**: Vision Transformer (ViT) - `google/vit-base-patch16-224-in21k`.
|
31 |
- **Input**: RGB images resized to 224x224 pixels.
|
32 |
- **Output**: Binary classification ("Real" or "Fake").
|