Upload ViT Base artifacts (weights + configs + preprocess)
Browse files- README.md +14 -13
- deepfake_vit_retrained.pth +3 -0
README.md
CHANGED
|
@@ -1,18 +1,19 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
tags:
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
---
|
| 8 |
|
| 9 |
-
# ViT Base – DeepFakeDetector
|
| 10 |
|
| 11 |
-
Vision Transformer (ViT-B/16) fine-tuned for binary deepfake detection.
|
| 12 |
|
| 13 |
-
## Labels
|
| 14 |
-
- 0 = real
|
| 15 |
-
- 1 = fake
|
| 16 |
|
| 17 |
-
## Output
|
| 18 |
-
- prob_fake ∈ [0,1] (softmax or sigmoid)
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- vision-transformer
|
| 5 |
+
- deepfake-detection
|
| 6 |
+
- image-classification
|
| 7 |
+
---
|
| 8 |
|
| 9 |
+
# ViT Base – DeepFakeDetector
|
| 10 |
|
| 11 |
+
Vision Transformer (ViT-B/16) fine-tuned for binary deepfake detection.
|
| 12 |
|
| 13 |
+
## Labels
|
| 14 |
+
- 0 = real
|
| 15 |
+
- 1 = fake
|
| 16 |
|
| 17 |
+
## Output
|
| 18 |
+
- prob_fake ∈ [0,1] (softmax or sigmoid)
|
| 19 |
+
|
deepfake_vit_retrained.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08db728d792f0084525b882d18089c142797b1bcfa12930448eda5f5f6e1cc57
|
| 3 |
+
size 1034521505
|