def fit(self,
x=None,
y=None,
batch_size=None,
epochs=1,
validation_data=None,
distributed=False,
**kwargs
):
"""
Train the model for a fixed num of epochs
Arguments:
:param x: Input data. It could be:
- a TFDataset object
- A Numpy array (or array-like), or a list of arrays
(in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors,
if the model has named inputs.
:param y: Target data. Like the input data `x`,
It should be consistent with `x` (you cannot have Numpy inputs and
tensor targets, or inversely). If `x` is a TFDataset, `y` should
not be specified (since targets will be obtained from `x`).
:param batch_size: Integer or `None`.
Number of samples per gradient update.
If `x` is a TFDataset, you do not need to specify batch_size.
:param epochs: Integer. Number of epochs to train the model.
An epoch is an iteration over the entire `x` and `y`
data provided.
:param 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.
`validation_data` could be:
- tuple `(x_val, y_val)` of Numpy arrays or tensors
:param distributed: Boolean. Whether to do prediction in distributed mode or local mode.
Default is True. In local mode, x must be a Numpy array.
"""
if isinstance(x, TFDataset):
# todo check arguments
assert validation_data is None, "validation_data must be None when " \
"using TFDataset as input, please " \
"use set the validation data in TFDataset"
if not x.has_batch:
raise ValueError("The batch_size of TFDataset must be " +
"specified when used in KerasModel fit.")
self._fit_distributed(x, epochs, **kwargs)
elif distributed:
dataset = TFDataset.from_ndarrays((x, y), val_tensors=validation_data,
batch_size=batch_size)
self._fit_distributed(dataset, epochs, **kwargs)
else:
self.model.fit(x=x,
y=y,
batch_size=batch_size,
epochs=epochs,
validation_data=validation_data,
**kwargs
)
def evaluate(self,
x=None,
y=None,
batch_per_thread=None,
distributed=False
):
"""
Evaluate a model on a given dataset
:param x: Input data. It could be:
- a TFDataset object
- A Numpy array (or array-like), or a list of arrays
(in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors,
if the model has named inputs.
:param y: Target data. Like the input data `x`,
It should be consistent with `x` (you cannot have Numpy inputs and
tensor targets, or inversely). If `x` is a TFDataset, `y` should
not be specified (since targets will be obtained from `x`).
:param batch_per_thread:
The default value is 1.
When distributed is True,the total batch size is batch_per_thread * rdd.getNumPartitions.
When distributed is False the total batch size is batch_per_thread * numOfCores.
:param distributed: Boolean. Whether to do prediction in distributed mode or local mode.
Default is True. In local mode, x must be a Numpy array.
"""
if isinstance(x, TFDataset):
if not x.has_batch:
raise ValueError("The batch_per_thread of TFDataset must be " +
"specified when used in KerasModel evaluate.")
if isinstance(x, TFNdarrayDataset):
x = _standarize_feature_label_dataset(x, self.model)
# todo check arguments
check_data_compatible(x, self.model, mode="evaluate")
return self._evaluate_distributed(x)
else:
if distributed:
dataset = TFDataset.from_ndarrays((x, y),
batch_per_thread=-1 if batch_per_thread is None
else batch_per_thread
)
dataset = _standarize_feature_label_dataset(dataset, self.model)
return self._evaluate_distributed(dataset)
else:
results = self.model.evaluate(x=x,
y=y,
batch_size=batch_per_thread)
results = dict(zip(self.metrics_names, results))
return results