Trains the model for a fixed number of epochs (iterations on a dataset).

fit(object, x, y, batch_size = NULL, epochs = 10, verbose = 1,
  callbacks = NULL, view_metrics = getOption("keras.view_metrics", default =
  "auto"), validation_split = 0, validation_data = NULL, shuffle = TRUE,
  class_weight = NULL, sample_weight = NULL, initial_epoch = 0,
  steps_per_epoch = NULL, validation_steps = NULL, ...)



Model to train.


Vector, matrix, or array of training data (or list if the model has multiple inputs). If all inputs in the model are named, you can also pass a list mapping input names to data.


Vector, matrix, or array of target data (or list if the model has multiple outputs). If all outputs in the model are named, you can also pass a list mapping output names to data.


Integer or NULL. Number of samples per gradient update. If unspecified, it will default to 32.


Number of epochs to train the model. Note that in conjunction with initial_epoch, the parameter epochs is to be understood as "final epoch". The model is not trained for a number of steps given by epochs, but until the epoch epochs is reached.


Verbosity mode (0 = silent, 1 = verbose, 2 = one log line per epoch).


List of callbacks to be called during training.


View realtime plot of training metrics (by epoch). The default ("auto") will display the plot when running within RStudio, metrics were specified during model compile(), epochs > 1 and verbose > 0. Use the global keras.view_metrics option to establish a different default.


Float between 0 and 1: fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch.


Data on which to evaluate the loss and any model metrics at the end of each epoch. The model will not be trained on this data. This could be a list (x_val, y_val) or a list (x_val, y_val, val_sample_weights).


TRUE to shuffle the training data before each epoch.


Optional named list mapping indices (integers) to a weight (float) to apply to the model's loss for the samples from this class during training. This can be useful to tell the model to "pay more attention" to samples from an under-represented class.


Optional array of the same length as x, containing weights to apply to the model's loss for each sample. In the case of temporal data, you can pass a 2D array with shape (samples, sequence_length), to apply a different weight to every timestep of every sample. In this case you should make sure to specify sample_weight_mode="temporal" in compile().


epoch at which to start training (useful for resuming a previous training run).


Total number of steps (batches of samples) before declaring one epoch finished and starting the next epoch. When training with Input Tensors such as TensorFlow data tensors, the default NULL is equal to the number of unique samples in your dataset divided by the batch size, or 1 if that cannot be determined.


Only relevant if steps_per_epoch is specified. Total number of steps (batches of samples) to validate before stopping.



See also

Other model functions: compile,, evaluate_generator, fit_generator, get_config, get_layer, keras_model_sequential, keras_model, multi_gpu_model, pop_layer,, predict_generator, predict_on_batch, predict_proba,, train_on_batch