Toggle Light / Dark / Auto color theme

Toggle table of contents sidebar

finetuner.tuner package

Subpackages

• finetuner.tuner.callback package
  • Submodules
    • finetuner.tuner.callback.base module
    • finetuner.tuner.callback.best_model_checkpoint module
    • finetuner.tuner.callback.early_stopping module
    • finetuner.tuner.callback.evaluation module
    • finetuner.tuner.callback.progress_bar module
    • finetuner.tuner.callback.training_checkpoint module
    • finetuner.tuner.callback.wandb_logger module
  • Module contents
• finetuner.tuner.dataset package
  • Submodules
    • finetuner.tuner.dataset.base module
    • finetuner.tuner.dataset.datasets module
    • finetuner.tuner.dataset.samplers module
  • Module contents
• finetuner.tuner.keras package
  • Submodules
    • finetuner.tuner.keras.data module
    • finetuner.tuner.keras.losses module
    • finetuner.tuner.keras.miner module
  • Module contents
• finetuner.tuner.miner package
  • Submodules
    • finetuner.tuner.miner.base module
    • finetuner.tuner.miner.mining_strategies module
  • Module contents
• finetuner.tuner.paddle package
  • Submodules
    • finetuner.tuner.paddle.datasets module
    • finetuner.tuner.paddle.losses module
    • finetuner.tuner.paddle.miner module
  • Module contents
• finetuner.tuner.pytorch package
  • Submodules
    • finetuner.tuner.pytorch.datasets module
    • finetuner.tuner.pytorch.losses module
    • finetuner.tuner.pytorch.miner module
  • Module contents

Submodules

• finetuner.tuner.augmentation module
• finetuner.tuner.base module
• finetuner.tuner.evaluation module
• finetuner.tuner.onnx module
• finetuner.tuner.state module

Module contents

finetuner.tuner.fit(embed_model, train_data, eval_data=None, preprocess_fn=None, collate_fn=None, epochs=10, batch_size=256, num_items_per_class=None, loss='SiameseLoss', configure_optimizer=None, learning_rate=0.001, scheduler_step='batch', device='cpu', callbacks=None, num_workers=0, **kwargs)

Finetune the model on the training data.

Parameters

• embed_model (AnyDNN) – an embedding model.

• train_data (DocumentArray) – Data on which to train the model.

• eval_data (Optional[ForwardRef]) – Data on which the validation loss is computed.

• preprocess_fn (Optional[ForwardRef]) – A pre-processing function, to apply pre-processing to documents on the fly. It should take as input the document in the dataset, and output whatever content the framework-specific dataloader (and model) would accept.

• collate_fn (Optional[ForwardRef]) – The collation function to merge the content of individual items into a batch. Should accept a list with the content of each item, and output a tensor (or a list/dict of tensors) that feed directly into the embedding model.

• epochs (int) – Number of epochs to train the model.

• batch_size (int) – The batch size to use for training and evaluation.

• num_items_per_class (Optional[int]) – Number of items from a single class to include in the batch. Only relevant for ClassDataset.

• loss (Union[str, ForwardRef]) – Which loss to use in training. Supported losses are: - SiameseLoss for Siamese network - TripletLoss for Triplet network

• configure_optimizer (Optional[Callable[[ForwardRef], Union[ForwardRef, Tuple[ForwardRef, ForwardRef]]]]) – A function that allows you to provide a custom optimizer and learning rate. The function should take one input - the embedding model, and return either just an optimizer or a tuple of an optimizer and a learning rate scheduler.

• learning_rate (float) – Learning rate for the default optimizer. If you provide a custom optimizer, this learning rate will not apply.

• scheduler_step (str) – At which interval should the learning rate sheduler’s step function be called. Valid options are “batch” and “epoch”.

• device (str) – The device to which to move the model. Supported options are "cpu" and "cuda" (for GPU).

• callbacks (Optional[List[ForwardRef]]) – A list of callbacks. The progress bar callback will be pre-prended to this list.

• num_workers (int) – Number of workers used for loading the data. This works only with Pytorch and Paddle Paddle, and has no effect when using a Keras model.

finetuner.tuner.save(embed_model, model_path, *args, **kwargs)

Save the embedding model.

Parameters

• embed_model (AnyDNN) – The embedding model to save.

• model_path (str) – Path to file/folder where to save the model.

• args – Arguments to pass to framework-specific tuner’s save method.

• kwargs – Keyword arguments to pass to framework-specific tuner’s save method.

Return type

None