From 1ebab144cc991ae87c24cc4434340f15a66956b5 Mon Sep 17 00:00:00 2001 From: zhanke Date: Wed, 14 Oct 2020 20:04:01 +0800 Subject: [PATCH] readme modify --- model_zoo/official/gnn/bgcf/README.md | 15 ++++++--------- model_zoo/official/gnn/gat/README.md | 3 ++- model_zoo/official/gnn/gcn/README.md | 4 +++- 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/model_zoo/official/gnn/bgcf/README.md b/model_zoo/official/gnn/bgcf/README.md index 5e561578bd..5a1b07deef 100644 --- a/model_zoo/official/gnn/bgcf/README.md +++ b/model_zoo/official/gnn/bgcf/README.md @@ -33,6 +33,7 @@ Specially, BGCF contains two main modules. The first is sampling, which produce aggregate the neighbors sampling from nodes consisting of mean aggregator and attention aggregator. # [Dataset](#contents) +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. - Dataset size: Statistics of dataset used are summarized as below: @@ -61,10 +62,6 @@ aggregate the neighbors sampling from nodes consisting of mean aggregator and at sh run_process_data_ascend.sh [SRC_PATH] ``` - - Launch - ``` - # Generate dataset in mindrecord format for Amazon-Beauty. - sh ./run_process_data_ascend.sh ./data # [Features](#contents) @@ -128,12 +125,12 @@ Parameters for both training and evaluation can be set in config.py. ```python "learning_rate": 0.001, # Learning rate - "num_epochs": 600, # Epoch sizes for training + "num_epoch": 600, # Epoch sizes for training "num_neg": 10, # Negative sampling rate "raw_neighs": 40, # Num of sampling neighbors in raw graph "gnew_neighs": 20, # Num of sampling neighbors in sample graph "input_dim": 64, # User and item embedding dimension - "l2_coeff": 0.03 # l2 coefficient + "l2": 0.03 # l2 coefficient "neighbor_dropout": [0.0, 0.2, 0.3]# Dropout ratio for different aggregation layer "num_graphs":5 # Num of sample graph ``` @@ -200,8 +197,8 @@ Parameters for both training and evaluation can be set in config.py. | Parameter | BGCF | | ------------------------------------ | ----------------------------------------- | | Resource | Ascend 910 | -| uploaded Date | | -| MindSpore Version | | +| uploaded Date | 09/23/2020(month/day/year) | +| MindSpore Version | 1.0.0 | | Dataset | Amazon-Beauty | | Training Parameter | epoch=600 | | Optimizer | Adam | @@ -209,7 +206,7 @@ Parameters for both training and evaluation can be set in config.py. | Recall@20 | 0.1534 | | NDCG@20 | 0.0912 | | Training Cost | 25min | -| Scripts | | +| Scripts | [bgcf script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/gnn/bgcf) | # [Description of random situation](#contents) diff --git a/model_zoo/official/gnn/gat/README.md b/model_zoo/official/gnn/gat/README.md index 3a560364ce..8dafd275d0 100644 --- a/model_zoo/official/gnn/gat/README.md +++ b/model_zoo/official/gnn/gat/README.md @@ -30,6 +30,7 @@ Graph Attention Networks(GAT) was proposed in 2017 by Petar Veličković et al. Note that according to whether this attention layer is the output layer of the network or not, the node update function can be concatenate or average. # [Dataset](#contents) +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. - Dataset size: Statistics of dataset used are summerized as below: @@ -175,7 +176,7 @@ Parameters for both training and evaluation can be set in config.py. | ------------------------------------ | ----------------------------------------- | | Resource | Ascend 910 | | uploaded Date | 06/16/2020(month/day/year) | -| MindSpore Version | 0.5.0-beta | +| MindSpore Version | 1.0.0 | | Dataset | Cora/Citeseer | | Training Parameter | epoch=200 | | Optimizer | Adam | diff --git a/model_zoo/official/gnn/gcn/README.md b/model_zoo/official/gnn/gcn/README.md index 9426dd5163..ada0fb0c02 100644 --- a/model_zoo/official/gnn/gcn/README.md +++ b/model_zoo/official/gnn/gcn/README.md @@ -28,6 +28,8 @@ GCN contains two graph convolution layers. Each layer takes nodes features and a # [Dataset](#contents) +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. + | Dataset | Type | Nodes | Edges | Classes | Features | Label rate | | ------- | ---------------: |-----: | ----: | ------: |--------: | ---------: | | Cora | Citation network | 2708 | 5429 | 7 | 1433 | 0.052 | @@ -162,7 +164,7 @@ Test set results: cost= 1.00983 accuracy= 0.81300 time= 0.39083 | -------------------------- | -------------------------------------------------------------- | | Resource | Ascend 910 | | uploaded Date | 06/09/2020 (month/day/year) | -| MindSpore Version | 0.5.0-beta | +| MindSpore Version | 1.0.0 | | Dataset | Cora/Citeseer | | Training Parameters | epoch=200 | | Optimizer | Adam |