AutoTrain documentation

Image Classification Parameters

You are viewing v0.8.21 version. A newer version v0.8.24 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Image Classification Parameters

class autotrain.trainers.image_classification.params.ImageClassificationParams

< >

( data_path: str = None model: str = 'google/vit-base-patch16-224' username: Optional = None lr: float = 5e-05 epochs: int = 3 batch_size: int = 8 warmup_ratio: float = 0.1 gradient_accumulation: int = 1 optimizer: str = 'adamw_torch' scheduler: str = 'linear' weight_decay: float = 0.0 max_grad_norm: float = 1.0 seed: int = 42 train_split: str = 'train' valid_split: Optional = None logging_steps: int = -1 project_name: str = 'project-name' auto_find_batch_size: bool = False mixed_precision: Optional = None save_total_limit: int = 1 token: Optional = None push_to_hub: bool = False eval_strategy: str = 'epoch' image_column: str = 'image' target_column: str = 'target' log: str = 'none' early_stopping_patience: int = 5 early_stopping_threshold: float = 0.01 )

Parameters

  • data_path (str) — Path to the dataset.
  • model (str) — Pre-trained model name or path. Default is “google/vit-base-patch16-224”.
  • username (Optional[str]) — Hugging Face account username.
  • lr (float) — Learning rate for the optimizer. Default is 5e-5.
  • epochs (int) — Number of epochs for training. Default is 3.
  • batch_size (int) — Batch size for training. Default is 8.
  • warmup_ratio (float) — Warmup ratio for learning rate scheduler. Default is 0.1.
  • gradient_accumulation (int) — Number of gradient accumulation steps. Default is 1.
  • optimizer (str) — Optimizer type. Default is “adamw_torch”.
  • scheduler (str) — Learning rate scheduler type. Default is “linear”.
  • weight_decay (float) — Weight decay for the optimizer. Default is 0.0.
  • max_grad_norm (float) — Maximum gradient norm for clipping. Default is 1.0.
  • seed (int) — Random seed for reproducibility. Default is 42.
  • train_split (str) — Name of the training data split. Default is “train”.
  • valid_split (Optional[str]) — Name of the validation data split.
  • logging_steps (int) — Number of steps between logging. Default is -1.
  • project_name (str) — Name of the project for output directory. Default is “project-name”.
  • auto_find_batch_size (bool) — Automatically find optimal batch size. Default is False.
  • mixed_precision (Optional[str]) — Mixed precision training mode (fp16, bf16, or None).
  • save_total_limit (int) — Maximum number of checkpoints to keep. Default is 1.
  • token (Optional[str]) — Hugging Face Hub token for authentication.
  • push_to_hub (bool) — Whether to push the model to Hugging Face Hub. Default is False.
  • eval_strategy (str) — Evaluation strategy during training. Default is “epoch”.
  • image_column (str) — Column name for images in the dataset. Default is “image”.
  • target_column (str) — Column name for target labels in the dataset. Default is “target”.
  • log (str) — Logging method for experiment tracking. Default is “none”.
  • early_stopping_patience (int) — Number of epochs with no improvement for early stopping. Default is 5.
  • early_stopping_threshold (float) — Threshold for early stopping. Default is 0.01.

ImageClassificationParams is a configuration class for image classification training parameters.

< > Update on GitHub