Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,25 @@
|
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
- kk
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
- f1
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
- f1
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
## Overview
|
| 11 |
+
|
| 12 |
+
**Model Name:** `ReDeepFake`
|
| 13 |
+
|
| 14 |
+
**Task:** Advanced Deepfake detection model for 2D flat images.
|
| 15 |
+
|
| 16 |
+
**Model Type:** Convolutional Neural Network (CNN) -> [EfficientNetB4](https://www.tensorflow.org/api_docs/python/tf/keras/applications/efficientnet) Model Architecture based.
|
| 17 |
+
|
| 18 |
+
**Framework:** `TensorFlow`
|
| 19 |
+
|
| 20 |
+
**Current Version:** V1.3
|
| 21 |
+
|
| 22 |
+
**Key Study:** [Deepfake Detection Challenge (DFDC)](https://www.kaggle.com/competitions/deepfake-detection-challenge) (in 2019-2020, by Meta, AWS, Microsoft and AI’s Media Integrity Steering Committee).
|
| 23 |
+
|
| 24 |
+
**Key Parthner:** `Microsoft Imagine Cup 2024`
|
| 25 |
+
|
| 26 |
+
**Kaggle Notebook:** https://www.kaggle.com/code/armanzhalgasbayev/deepfake-detection-efficientnetb4-tf-cnn
|