Aller au contenu
ModelPrésentéExterne
Télécharger

Siftformer 1.5

| Index | Class | | 0 | 정상 (normal) | | 1 | 졸음 (drowsy) | | 2 | 주의분산 (distracted) | | 3 | 폭행 (violence) |

Sourcehuggingface.co/koreashin/siftformer-1.5/tree/8f49ab6736b6ce44defe4726daacb4fc7150eb6b
TypeOtherVersionPytorch modelCClasse

Source du modèle

Type
Other
Taille du fichier
18,7 MB
Version
vPytorch model
Mis à jour
11 oct. 2026
Source
Hugging Face

Description de la source

SiftFormer 1.5

Classes

IndexClass
0정상 (normal)
1졸음 (drowsy)
2주의분산 (distracted)
3폭행 (violence)

Input

  • Shape: [B, T, C, H, W]
  • T = 30 frames
  • H = W = 224
  • C = 3 (RGB)
  • ImageNet normalization (mean [0.485, 0.456, 0.406], std [0.229, 0.224, 0.225])
  • dtype: float32 or bfloat16

Sources

1 source
Hugging FacePrincipalVersion 8f49ab6736b6ce44defe4726daacb4fc7150eb6b
huggingface.co/koreashin/siftformer-1.5/tree/8f49ab6736b6ce44defe4726daacb4fc7150eb6b

Vérifié 11 oct.

Artefacts du modèle

1 artefact

pytorch_model.bin

bin · 18,7 MB · SHA-256 b6e0769b9167…2288 · Hugging Face

Download file

Extraits de sources

2 extraits
Readme2 aoûthuggingface.co/koreashin/siftformer-1.5

--- license: apache-2.0 tags: - video-classification - driver-behavior pipeline_tag: video-classification --- # SiftFormer 1.5 ## Classes | Index | Class | |-------|-------| | 0 | 정상 (normal) | | 1 | 졸음 (drowsy) | | 2 | 주의분산 (distracted) | | 3 | 폭행 (violence) | ## Input - Shape: `[B, T, C, H, W]` - `T = 30` frames - `H = W = 224` - `C = 3` (RGB) - ImageNet normalization (mean `[0.485, 0.456, 0.406]`, std `[0.229, 0.224, 0.225]`) - dtype: `float32` or `bfloat16`

Note2 aoûthuggingface.co/koreashin/siftformer-1.5

Source context: 0 downloads · 0 likes · Pipeline video-classification · Repo koreashin/siftformer-1.5