This function delegates most work to keras::fit.keras.engine.training.Model()
and performs additional consistency
checks to make sure tf_compile_model()
was called with the appropriate options to support fitting the observations
y
as well as automatically converting y
to a n x 6 matrix needed by the compiled loss function.
Usage
# S3 method for reservr_keras_model
fit(
object,
x,
y,
batch_size = NULL,
epochs = 10,
verbose = getOption("keras.fit_verbose", default = 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,
...
)
Arguments
- object
A compiled
reservr_keras_model
as obtained bytf_compile_model()
.- x
A list of input tensors (predictors)
- y
A
trunc_obs
tibble of observed outcomes, or something convertible viaas_trunc_obs()
.- batch_size
Integer or
NULL
. Number of samples per gradient update. If unspecified,batch_size
will default to 32.- epochs
Number of epochs to train the model. Note that in conjunction with
initial_epoch
,epochs
is to be understood as "final epoch". The model is not trained for a number of iterations given byepochs
, but merely until the epoch of indexepochs
is reached.- verbose
Verbosity mode (0 = silent, 1 = progress bar, 2 = one line per epoch). Defaults to 1 in most contexts, 2 if in knitr render or running on a distributed training server.
- callbacks
List of callbacks to be called during training.
- view_metrics
View realtime plot of training metrics (by epoch). The default (
"auto"
) will display the plot when running within RStudio,metrics
were specified during modelcompile()
,epochs > 1
andverbose > 0
. Use the globalkeras.view_metrics
option to establish a different default.- validation_split
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. The validation data is selected from the last samples in the
x
andy
data provided, before shuffling.- validation_data
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).
validation_data
will overridevalidation_split
.- shuffle
shuffle: Logical (whether to shuffle the training data before each epoch) or string (for "batch"). "batch" is a special option for dealing with the limitations of HDF5 data; it shuffles in batch-sized chunks. Has no effect when
steps_per_epoch
is notNULL
.- class_weight
Optional named list mapping indices (integers) to a weight (float) value, used for weighting the loss function (during training only). This can be useful to tell the model to "pay more attention" to samples from an under-represented class.
- sample_weight
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"
incompile()
.- initial_epoch
Integer, Epoch at which to start training (useful for resuming a previous training run).
- steps_per_epoch
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 samples in your dataset divided by the batch size, or 1 if that cannot be determined.- validation_steps
Only relevant if
steps_per_epoch
is specified. Total number of steps (batches of samples) to validate before stopping.- ...
Unused. If old arguments are supplied, an error message will be raised informing how to fix the issue.
Value
A history
object that contains all information collected during training.
The model object will be updated in-place as a side-effect.
Details
Additionally, the default batch_size
is min(nrow(y), 10000)
instead of keras default of 32
because the latter
is a very bad choice for fitting most distributions since the involved loss is much less stable than typical losses
used in machine learning, leading to divergence for small batch sizes.
Examples
dist <- dist_exponential()
params <- list(rate = 1.0)
N <- 100L
rand_input <- runif(N)
x <- dist$sample(N, with_params = params)
if (interactive() && keras::is_keras_available()) {
tf_in <- keras::layer_input(1L)
mod <- tf_compile_model(
inputs = list(tf_in),
intermediate_output = tf_in,
dist = dist,
optimizer = keras::optimizer_adam(),
censoring = FALSE,
truncation = FALSE
)
tf_fit <- fit(
object = mod,
x = k_matrix(rand_input),
y = x,
epochs = 10L,
callbacks = list(
callback_debug_dist_gradients(mod, k_matrix(rand_input), x, keep_grads = TRUE)
)
)
}