From fcc40964917f984dc3b500d10303ce2aa106b783 Mon Sep 17 00:00:00 2001 From: liaogang Date: Wed, 31 Aug 2016 07:13:52 +0000 Subject: [PATCH] rename paraphase_model to paraphrase_model ISSUE=4604681 git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1452 1ad973e4-5ce8-4261-8a94-b56d1f490c56 --- doc/demo/embedding_model/index.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/doc/demo/embedding_model/index.md b/doc/demo/embedding_model/index.md index b544492e47f..45992ad856e 100644 --- a/doc/demo/embedding_model/index.md +++ b/doc/demo/embedding_model/index.md @@ -54,11 +54,11 @@ The general command of extracting desired parameters from the pretrained embeddi Here, you can simply run the command: cd $PADDLE_ROOT/demo/seqToseq/data/ - ./paraphase_model.sh + ./paraphrase_model.sh And you will see following embedding model structure: - paraphase_model + paraphrase_model |--- _source_language_embedding |--- _target_language_embedding @@ -90,7 +90,7 @@ Then, train the model by running the command: where `train.sh` is almost the same as `demo/seqToseq/translation/train.sh`, the only difference is following two command arguments: -- `--init_model_path`: path of the initialization model, here is `data/paraphase_model` +- `--init_model_path`: path of the initialization model, here is `data/paraphrase_model` - `--load_missing_parameter_strategy`: operations when model file is missing, here use a normal distibution to initialize the other parameters except for the embedding layer For users who want to understand the dataset format, model architecture and training procedure in detail, please refer to [Text generation Tutorial](text_generation.md). -- GitLab