From 99f0592926cc557bc271c5e5ff31c5cc04dd024f Mon Sep 17 00:00:00 2001 From: chenhaozhe Date: Thu, 12 Aug 2021 11:09:01 +0800 Subject: [PATCH] update bert readme --- model_zoo/official/nlp/bert/README.md | 8 ++++---- model_zoo/official/nlp/bert/README_CN.md | 8 +++++--- model_zoo/official/nlp/bert/scripts/run_infer_310.sh | 4 +++- 3 files changed, 12 insertions(+), 8 deletions(-) diff --git a/model_zoo/official/nlp/bert/README.md b/model_zoo/official/nlp/bert/README.md index adcfd23d1ba..382e8766ed0 100644 --- a/model_zoo/official/nlp/bert/README.md +++ b/model_zoo/official/nlp/bert/README.md @@ -654,8 +654,10 @@ The result will be as follows: - Export on local +We only support export with fine-tuned downstream task model and yaml config file, because the pretrained model is useless in inferences task. + ```shell -python export.py --config_path [../../*.yaml] --ckpt_file [CKPT_PATH] --file_name [FILE_NAME] --file_format [FILE_FORMAT] +python export.py --config_path [../../*.yaml] --export_ckpt_file [CKPT_PATH] --export_file_name [FILE_NAME] --file_format [FILE_FORMAT] ``` - Export on ModelArts (If you want to run in modelarts, please check the official documentation of [modelarts](https://support.huaweicloud.com/modelarts/), and you can start as follows) @@ -686,8 +688,7 @@ python export.py --config_path [../../*.yaml] --ckpt_file [CKPT_PATH] --file_nam # You will see bert_ner.mindir under {Output file path}. ``` -The ckpt_file parameter is required, -`EXPORT_FORMAT` should be in ["AIR", "MINDIR"] +The `export_ckpt_file` parameter is required, and `file_format` should be in ["AIR", "MINDIR"] ### [Inference Process](#contents) @@ -799,4 +800,3 @@ Refer to the [ModelZoo FAQ](https://gitee.com/mindspore/mindspore/tree/master/mo - **Q: Why the training process failed with error for the shape can not match?** **A**: This is usually caused by the config `seq_length` of model can't match the dataset. You could check and modified the `seq_length` in yaml config according to the dataset you used. The parameter of model won't change with `seq_length`, the shapes of parameter only depends on model config `max_position_embeddings`. - diff --git a/model_zoo/official/nlp/bert/README_CN.md b/model_zoo/official/nlp/bert/README_CN.md index 8d7a13e383b..e0d53f64e86 100644 --- a/model_zoo/official/nlp/bert/README_CN.md +++ b/model_zoo/official/nlp/bert/README_CN.md @@ -613,10 +613,12 @@ bash scripts/squad.sh ## 导出mindir模型 +由于预训练模型通常没有应用场景，需要经过下游任务的finetune之后才能使用，所以当前仅支持使用下游任务模型和yaml配置文件进行export操作。 + - 在本地导出 ```shell -python export.py --config_path [../../*.yaml] --ckpt_file [CKPT_PATH] --file_name [FILE_NAME] --file_format [FILE_FORMAT] +python export.py --config_path [../../*.yaml] --export_ckpt_file [CKPT_PATH] --export_file_name [FILE_NAME] --file_format [FILE_FORMAT] ``` - 在ModelArts上导出 @@ -647,7 +649,7 @@ python export.py --config_path [../../*.yaml] --ckpt_file [CKPT_PATH] --file_nam # 你将在{Output file path}下看到 'bert_ner.mindir'文件 ``` -参数`ckpt_file` 是必需的，`EXPORT_FORMAT` 必须在 ["AIR", "MINDIR"]中进行选择。 +参数`export_ckpt_file` 是必需的，`file_format` 必须在 ["AIR", "MINDIR"]中进行选择。 ## 推理过程 @@ -753,4 +755,4 @@ run_pretrain.py中设置了随机种子，确保分布式训练中每个节点 **A**： 持续溢出通常是因为使用了较高的学习率导致训练不收敛。可以考虑修改yaml配置文件中的参数，调低`learning_rate`来降低初始学习率或提高`power`加速学习率衰减。 - **Q: 运行报错shape不匹配是什么问题？** - **A**： Bert模型中的shape不匹配通常是因为模型参数配置和使用的数据集规格不匹配，主要是句长问题，可以考虑修改`seq_length`参数来匹配所使用的具体数据集。改变该参数不影响权重的规格，权重的规格仅与`max_position_embeddings`参数有关。 \ No newline at end of file + **A**： Bert模型中的shape不匹配通常是因为模型参数配置和使用的数据集规格不匹配，主要是句长问题，可以考虑修改`seq_length`参数来匹配所使用的具体数据集。改变该参数不影响权重的规格，权重的规格仅与`max_position_embeddings`参数有关。 diff --git a/model_zoo/official/nlp/bert/scripts/run_infer_310.sh b/model_zoo/official/nlp/bert/scripts/run_infer_310.sh index 61b85bb6257..acd330e027c 100644 --- a/model_zoo/official/nlp/bert/scripts/run_infer_310.sh +++ b/model_zoo/official/nlp/bert/scripts/run_infer_310.sh @@ -23,7 +23,9 @@ exit 1 fi get_real_path(){ - if [ "${1:0:1}" == "/" ]; then + if [ -z "$1" ]; then + echo "" + elif [ "${1:0:1}" == "/" ]; then echo "$1" else echo "$(realpath -m $PWD/$1)"