first

swtich to Docker Hub from Google Cloud Registry

Dockerfile

@@ -1,4 +1,4 @@
-FROM gcr.io/tensorflow/tensorflow:1.3.0
+FROM tensorflow/tensorflow:1.3.0
 
 RUN pip install networkx==1.11
 RUN rm /notebooks/*

Dockerfile.gpu

@@ -1,4 +1,4 @@
-FROM gcr.io/tensorflow/tensorflow:1.3.0-gpu
+FROM tensorflow/tensorflow:1.3.0-gpu
 
 RUN pip install networkx==1.11
 RUN rm /notebooks/*

README.md

@@ -7,6 +7,7 @@
 
 ### Overview
 
+
 This directory contains code necessary to run the GraphSage algorithm.
 GraphSage can be viewed as a stochastic generalization of graph convolutions, and it is especially useful for massive, dynamic graphs that contain rich feature information.
 See our [paper](https://arxiv.org/pdf/1706.02216.pdf) for details on the algorithm.
@@ -35,7 +36,11 @@ If you make use of this code or the GraphSage algorithm in your work, please cit
 
 ### Requirements
 
-Recent versions of TensorFlow, numpy, scipy, and networkx are required (but networkx must be <=1.11). To guarantee that you have the right package versions, you can use [docker](https://docs.docker.com/) to easily set up a virtual environment. See the Docker subsection below for more info. 
+Recent versions of TensorFlow, numpy, scipy, sklearn, and networkx are required (but networkx must be <=1.11). You can install all the required packages using the following command:
+
+	$ pip install -r requirements.txt
+
+To guarantee that you have the right package versions, you can use [docker](https://docs.docker.com/) to easily set up a virtual environment. See the Docker subsection below for more info.
 
 #### Docker
 

graphsage/models.py

@@ -477,7 +477,7 @@ class Node2VecModel(GeneralizedModel):
 
     def _loss(self):
         aff = tf.reduce_sum(tf.multiply(self.outputs1, self.outputs2), 1) + self.outputs2_bias
-        neg_aff = tf.matmul(self.outputs2, tf.transpose(self.neg_outputs)) + self.neg_outputs_bias
+        neg_aff = tf.matmul(self.outputs1, tf.transpose(self.neg_outputs)) + self.neg_outputs_bias
         true_xent = tf.nn.sigmoid_cross_entropy_with_logits(
                 labels=tf.ones_like(aff), logits=aff)
         negative_xent = tf.nn.sigmoid_cross_entropy_with_logits(

graphsage/utils.py

@@ -8,7 +8,7 @@ import os
 
 import networkx as nx
 from networkx.readwrite import json_graph
-version_info = map(int, nx.__version__.split('.'))
+version_info = list(map(int, nx.__version__.split('.')))
 major = version_info[0]
 minor = version_info[1]
 assert (major <= 1) and (minor <= 11), "networkx major version > 1.11"

requirements.txt

@@ -0,0 +1,25 @@
+absl-py==0.2.2
+astor==0.6.2
+backports.weakref==1.0.post1
+bleach==1.5.0
+decorator==4.3.0
+enum34==1.1.6
+funcsigs==1.0.2
+futures==3.2.0
+gast==0.2.0
+grpcio==1.12.1
+html5lib==0.9999999
+Markdown==2.6.11
+mock==2.0.0
+networkx==1.11
+numpy==1.14.5
+pbr==4.0.4
+protobuf==3.6.0
+scikit-learn==0.19.1
+scipy==1.1.0
+six==1.11.0
+sklearn==0.0
+tensorboard==1.8.0
+tensorflow==1.8.0
+termcolor==1.1.0
+Werkzeug==0.14.1