dmlc--dgl
nv-dlasalle
f673fc2553
* Add async transferer class * Add async ndarray copy interface * Add python bindings * Fix comment * Add python class * Fix linting issues * Add python unit test * Update python interface * move async_transferer to cuda only directory * Fix linting issue * Move out of contrib * Add doc strings * Move test compute from backend * Update comment * Fix test naming * Fix argument usage * Wrap/unwrap backend parameters * Move to dataloading * Move to 'dataloading' * Make GPU/CPU compatible * Fix unit tests * Add docs * Use only backend interface for datamovement in unit test
27 行
832 B
Python
27 行
832 B
Python
"""The ``dgl.dataloading`` package contains:
|
|
|
|
* Data loader classes for iterating over a set of nodes or edges in a graph and generates
|
|
computation dependency via neighborhood sampling methods.
|
|
|
|
* Various sampler classes that perform neighborhood sampling for multi-layer GNNs.
|
|
|
|
* Negative samplers for link prediction.
|
|
|
|
For a holistic explanation on how different components work together.
|
|
Read the user guide :ref:`guide-minibatch`.
|
|
|
|
.. note::
|
|
This package is experimental and the interfaces may be subject
|
|
to changes in future releases. It currently only has implementations in PyTorch.
|
|
"""
|
|
from .neighbor import *
|
|
from .dataloader import *
|
|
|
|
from . import negative_sampler
|
|
from .async_transferer import AsyncTransferer
|
|
|
|
from .. import backend as F
|
|
|
|
if F.get_preferred_backend() == 'pytorch':
|
|
from .pytorch import *
|