lukhsaankumar/DeepFakeDetectorBackend-storage / .hf_cache /DeepFakeDetector--vit-base-final
2.78 GB
70 files
Updated 25 days ago
NameSize
.cache
.gitattributes1.52 kB
xet
README.md326 Bytes
xet
config.json326 Bytes
xet
deepfake_vit_finetuned_wildfake.pth1.03 GB
xet
deepfake_vit_retrained.pth1.03 GB
xet
finetuned_base_vit_march5.pth345 MB
xet
label_map.json32 Bytes
xet
preprocess.json191 Bytes
xet
vit-base-final.pth345 MB
xet
README.md

license: apache-2.0 tags: - vision-transformer - deepfake-detection - image-classification

ViT Base – DeepFakeDetector

Vision Transformer (ViT-B/16) fine-tuned for binary deepfake detection.

Labels

  • 0 = real
  • 1 = fake

Output

  • prob_fake ∈ [0,1] (softmax or sigmoid)
Total size
2.78 GB
Files
70
Last updated
Apr 21
Pre-warmed CDN
US EU US EU

Contributors