Merge pull request #391 from yinhaofeng/ncf

Ncf
PaddlePaddle · Mar 23, 2021 · 623e14d · 623e14d
2 parents 26ef070 + f7caf1d
commit 623e14d
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/models/recall/ncf/config.yaml b/models/recall/ncf/config.yaml
@@ -24,7 +24,7 @@ runner:
 
   test_data_dir: "data/test"
   infer_reader_path: "movielens_reader"  # importlib format
-  infer_batch_size: 5
+  infer_batch_size: 1
   infer_load_path: "output_model_ncf"
   infer_start_epoch: 2
   infer_end_epoch: 3

diff --git a/models/recall/ncf/readme.md b/models/recall/ncf/readme.md
@@ -61,7 +61,7 @@ os : windows/linux/macos
 # 动态图训练
 python -u ../../../tools/trainer.py -m config.yaml # 全量数据运行config_bigdata.yaml 
 # 动态图预测
-python -u infer.py -m config.yaml 
+python -u ../../../tools/infer.py -m config.yaml 
 
 # 静态图训练
 python -u ../../../tools/static_trainer.py -m config.yaml # 全量数据运行config_bigdata.yaml 
@@ -85,11 +85,13 @@ python -u ../../../tools/static_infer.py -m config.yaml
 
 1. 确认您当前所在目录为PaddleRec/models/recall/ncf  
 2. 进入paddlerec/datasets/movielens_pinterest_NCF目录下，执行该脚本，会从国内源的服务器上下载我们预处理完成的movielens和pinterest全量数据集，并解压到指定文件夹。
+
 ``` bash
 cd ../../../datasets/movielens_pinterest_NCF
 sh run.sh
 ```
 3. 切回模型目录,执行命令运行全量数据
+
 ```bash
 cd - # 切回模型目录
 # 动态图训练并得到指标(这里需要使用bash启动脚本)