tlt.models.image_classification.tfhub_image_classification_model.TFHubImageClassificationModel.train

TFHubImageClassificationModel.train(dataset: ImageClassificationDataset, output_dir, epochs=1, initial_checkpoints=None, do_eval=True, early_stopping=False, lr_decay=True, enable_auto_mixed_precision=None, shuffle_files=True, seed=None, extra_layers=None, distributed=False, hostfile=None, nnodes=1, nproc_per_node=1, callbacks=None, **kwargs)[source]

Trains the model using the specified image classification dataset. The first time training is called, it will get the feature extractor layer from TF Hub and add on a dense layer based on the number of classes in the specified dataset. The model is compiled and trained for the specified number of epochs. If a path to initial checkpoints is provided, those weights are loaded before training.

Parameters

  • dataset (ImageClassificationDataset) – Dataset to use when training the model

  • output_dir (str) – Path to a writeable directory for checkpoint files

  • epochs (int) – Number of epochs to train the model (default: 1)

  • initial_checkpoints (str) – Path to checkpoint weights to load. If the path provided is a directory, the latest checkpoint will be used.

  • do_eval (bool) – If do_eval is True and the dataset has a validation subset, the model will be evaluated

  • early_stopping (bool) – Enable early stopping if convergence is reached while training at the end of each epoch.

  • lr_decay (bool) – If lr_decay is True and do_eval is True, learning rate decay on the validation loss is applied at the end of each epoch.

  • enable_auto_mixed_precision (bool or None) – Enable auto mixed precision for training. Mixed precision uses both 16-bit and 32-bit floating point types to make training run faster and use less memory. It is recommended to enable auto mixed precision training when running on platforms that support bfloat16 (Intel third or fourth generation Xeon processors). If it is enabled on a platform that does not support bfloat16, it can be detrimental to the training performance. If enable_auto_mixed_precision is set to None, auto mixed precision will be automatically enabled when running with Intel fourth generation Xeon processors, and disabled for other platforms.

  • shuffle_files (bool) – Boolean specifying whether to shuffle the training data before each epoch.

  • seed (int) – Optionally set a seed for reproducibility.

  • extra_layers (list[int]) – Optionally insert additional dense layers between the base model and output layer. This can help increase accuracy when fine-tuning a TFHub model. The input should be a list of integers representing the number and size of the layers, for example [1024, 512] will insert two dense layers, the first with 1024 neurons and the second with 512 neurons.

  • callbacks (list) – List of keras.callbacks.Callback instances to apply during training.

Returns

History object from the model.fit() call

Raises

  • FileExistsError – if the output directory is a file

  • TypeError – if the dataset specified is not an ImageClassificationDataset

  • TypeError – if the output_dir parameter is not a string

  • TypeError – if the epochs parameter is not a integer

  • TypeError – if the initial_checkpoints parameter is not a string

  • TypeError – if the extra_layers parameter is not a list of integers