tf.estimator.inputs.numpy_input_fn(
x,
y=None,
batch_size=128,
num_epochs=1,
shuffle=None,
queue_capacity=1000,
num_threads=1
)
Returns input function that would feed dict of numpy arrays into the model.
This returns a function outputting features
and targets
based on the dict
of numpy arrays. The dict features
has the same keys as the x
. The dict
targets
has the same keys as the y
if y
is a dict.
Example:
age = np.arange(4) * 1.0
height = np.arange(32, 36)
x = {'age': age, 'height': height}
y = np.arange(-32, -28)
with tf.Session() as session:
input_fn = numpy_io.numpy_input_fn(
x, y, batch_size=2, shuffle=False, num_epochs=1)
Args:
x
: numpy array object or dict of numpy array objects. If an array, the array will be treated as a single feature.y
: numpy array object or dict of numpy array object.None
if absent.batch_size
: Integer, size of batches to return.num_epochs
: Integer, number of epochs to iterate over data. IfNone
will run forever.shuffle
: Boolean, if True shuffles the queue. Avoid shuffle at prediction time.queue_capacity
: Integer, size of queue to accumulate.num_threads
: Integer, number of threads used for reading and enqueueing. In order to have predicted and repeatable order of reading and enqueueing, such as in prediction and evaluation mode,num_threads
should be 1.
Returns:
Function, that has signature of ()->(dict of features
, targets
)
Raises:
ValueError
: if the shape ofy
mismatches the shape of values inx
(i.e., values inx
have same shape).ValueError
: if duplicate keys are in bothx
andy
wheny
is a dict.ValueError
: if x or y is an empty dict.TypeError
:x
is not a dict or array.ValueError
: if 'shuffle' is not provided or a bool.