config.json

{
  "architectures": ["DriverBehaviorModel"],
  "model_type": "video-swin-transformer",
  "backbone": "swin3d_t",
  "num_classes": 5,
  "class_names": ["정상", "졸음운전", "물건찾기", "휴대폰 사용", "운전자 폭행"],
  "input_size": [3, 30, 224, 224],
  "pretrained_backbone": "Kinetics-400",
  "head": {
    "type": "Sequential",
    "layers": ["LayerNorm(768)", "Dropout(0.3)", "Linear(768, 5)"]
  },
  "training": {
    "epoch": 2,
    "accuracy": 0.9515,
    "macro_f1": 0.9392,
    "batch_size": 32,
    "optimizer": "AdamW",
    "learning_rate": 1e-3,
    "weight_decay": 0.05,
    "scheduler": "OneCycleLR",
    "mixed_precision": "fp16",
    "augmentation": ["Mixup(0.4)", "RandomResizedCrop", "HorizontalFlip", "ColorJitter", "TemporalAugmentation"]
  },
  "performance": {
    "정상": {"precision": 0.91, "recall": 0.95, "f1": 0.93},
    "졸음운전": {"precision": 0.99, "recall": 0.97, "f1": 0.98},
    "물건찾기": {"precision": 0.92, "recall": 0.88, "f1": 0.90},
    "휴대폰 사용": {"precision": 0.84, "recall": 0.93, "f1": 0.88},
    "운전자 폭행": {"precision": 1.00, "recall": 1.00, "f1": 1.00}
  }
}