Deressa commited on
Commit
fcf5b2f
·
1 Parent(s): 7ec25da

Minor fix.

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -5,7 +5,7 @@ language:
5
  ---
6
  Pretrained model for Deepfake Video Detection Using Generative Convolutional Vision Transformer (GenConViT) paper.
7
 
8
- #GenConViT Model Architecture
9
 
10
  The GenConViT model consists of two independent networks and incorporates the following modules:
11
 
@@ -14,7 +14,9 @@ The GenConViT model consists of two independent networks and incorporates the fo
14
  ConvNeXt-Swin Hybrid layer
15
 
16
  GenConViT is trained using Adam optimizer with a learning rate of 0.0001 and weight decay of 0.0001.
 
17
  GenConViT is trained on the DFDC, FF++, and TM datasets.
 
18
  GenConViT model has an average accuracy of 95.8% and an AUC value of 99.3% across the tested datasets (DFDC, FF++, and DeepfakeTIMT, Celeb-DF (v2)).
19
 
20
  code link: https://github.com/erprogs/GenConViT
 
5
  ---
6
  Pretrained model for Deepfake Video Detection Using Generative Convolutional Vision Transformer (GenConViT) paper.
7
 
8
+ GenConViT Model Architecture
9
 
10
  The GenConViT model consists of two independent networks and incorporates the following modules:
11
 
 
14
  ConvNeXt-Swin Hybrid layer
15
 
16
  GenConViT is trained using Adam optimizer with a learning rate of 0.0001 and weight decay of 0.0001.
17
+
18
  GenConViT is trained on the DFDC, FF++, and TM datasets.
19
+
20
  GenConViT model has an average accuracy of 95.8% and an AUC value of 99.3% across the tested datasets (DFDC, FF++, and DeepfakeTIMT, Celeb-DF (v2)).
21
 
22
  code link: https://github.com/erprogs/GenConViT