提交 e8cc247f 编写于 作者: L liweibin

update

上级 98e82403
docs/source/_static/logo.png

49.1 KB | W: | H:

docs/source/_static/logo.png

50.4 KB | W: | H:

docs/source/_static/logo.png
docs/source/_static/logo.png
docs/source/_static/logo.png
docs/source/_static/logo.png
  • 2-up
  • Swipe
  • Onion skin
...@@ -73,13 +73,12 @@ lanaguage = "zh_cn" ...@@ -73,13 +73,12 @@ lanaguage = "zh_cn"
html_theme = "sphinx_rtd_theme" html_theme = "sphinx_rtd_theme"
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
html_show_sourcelink = False html_show_sourcelink = False
#html_logo = 'pgl_logo.png' html_logo = '_static/logo.png'
# Add any paths that contain custom static files (such as style sheets) here, # Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files, # relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css". # so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static'] html_static_path = ['_static']
'''
html_theme_options = { html_theme_options = {
'canonical_url': '', 'canonical_url': '',
'analytics_id': 'UA-XXXXXXX-1', # Provided by Google in your dashboard 'analytics_id': 'UA-XXXXXXX-1', # Provided by Google in your dashboard
...@@ -96,4 +95,3 @@ html_theme_options = { ...@@ -96,4 +95,3 @@ html_theme_options = {
'includehidden': True, 'includehidden': True,
'titles_only': False 'titles_only': False
} }
'''
# Paddle Graph Learning (PGL) # Paddle Graph Learning (PGL)
<div />
<div align=left><img src="_static/logo.png" width="300"></div>
<div />
Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle). Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle).
......
...@@ -20,7 +20,7 @@ Some important hyper parameters in config.yaml: ...@@ -20,7 +20,7 @@ Some important hyper parameters in config.yaml:
- **use_cuda**: use GPU to train model - **use_cuda**: use GPU to train model
- **data_path**: the directory of dataset that you want to load - **data_path**: the directory of dataset that you want to load
- **lr**: learning rate - **lr**: learning rate
- **neg_num**: number of negatie samples. - **neg_num**: number of negative samples.
- **num_walks**: number of walks started from each node - **num_walks**: number of walks started from each node
- **walk_length**: walk length - **walk_length**: walk length
- **metapath**: meta path scheme - **metapath**: meta path scheme
......
...@@ -16,6 +16,7 @@ ...@@ -16,6 +16,7 @@
from pgl.layers import conv from pgl.layers import conv
from pgl.layers.conv import * from pgl.layers.conv import *
from pgl.layers import set2set
from pgl.layers.set2set import * from pgl.layers.set2set import *
__all__ = [] __all__ = []
......
...@@ -23,6 +23,8 @@ import paddle.fluid.layers as L ...@@ -23,6 +23,8 @@ import paddle.fluid.layers as L
import pgl import pgl
__all__ = ['Set2Set']
class Set2Set(object): class Set2Set(object):
"""Implementation of set2set pooling operator. """Implementation of set2set pooling operator.
......
...@@ -223,9 +223,10 @@ def scatter_add(input, index, updates): ...@@ -223,9 +223,10 @@ def scatter_add(input, index, updates):
Same type and shape as input. Same type and shape as input.
""" """
output = fluid.layers.scatter(input, index, updates, mode='add') output = fluid.layers.scatter(input, index, updates, overwrite=False)
return output return output
def scatter_max(input, index, updates): def scatter_max(input, index, updates):
"""Scatter max updates to input by given index. """Scatter max updates to input by given index.
...@@ -244,4 +245,3 @@ def scatter_max(input, index, updates): ...@@ -244,4 +245,3 @@ def scatter_max(input, index, updates):
output = fluid.layers.scatter(input, index, updates, mode='max') output = fluid.layers.scatter(input, index, updates, mode='max')
return output return output
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册