mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

!17990 bgcf readme amend 

Merge pull request !17990 from 张晓晓/bgcf_readme
This commit is contained in:
i-robot 2021-06-09 09:52:48 +08:00 committed by Gitee
parent 90c9c2b8bc 4270205f00
commit fb866c8030
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
model_zoo/official/gnn/bgcf/README.md
View File

@ -320,7 +320,7 @@ python export.py --ckpt_file [CKPT_PATH] --file_name [FILE_NAME] --file_format [
``` ```
The ckpt_file parameter is required, The ckpt_file parameter is required,
`EXPORT_FORMAT` should be in ["AIR", "MINDIR"] `file_format` should be in ["AIR", "MINDIR"]
### Infer on Ascend310 ### Infer on Ascend310
@ -331,7 +331,7 @@ Before performing inference, the mindir file must be exported by `export.py` scr
bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [NEED_PREPROCESS] [DEVICE_ID] bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [NEED_PREPROCESS] [DEVICE_ID]
``` ```
- `NEED_PREPROCESS` means weather need preprocess or not, it's value is 'y' or 'n'. - `NEED_PREPROCESS` means weather the original dataset processed in the mindrecord format needs to be converted to the binary format, it's value is 'y' or 'n'.
- `DEVICE_ID` is optional, default value is 0. - `DEVICE_ID` is optional, default value is 0.
### result ### result

6
model_zoo/official/gnn/bgcf/README_CN.md
View File

@ -343,18 +343,18 @@ python export.py --ckpt_file [CKPT_PATH] --file_name [FILE_NAME] --file_format [
``` ```
参数ckpt_file为必填项， 参数ckpt_file为必填项，
`EXPORT_FORMAT` 必须在 ["AIR", "MINDIR"]中选择。 `file_format` 必须在 ["AIR", "MINDIR"]中选择。
### 在Ascend310执行推理 ### 在Ascend310执行推理
在执行推理前，mindir文件必须通过`export.py`脚本导出。以下展示了使用minir模型执行推理的示例。 在执行推理前，mindir文件必须通过`export.py`脚本导出。以下展示了使用mindir模型执行推理的示例。
```shell ```shell
# Ascend310 inference # Ascend310 inference
bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [NEED_PREPROCESS] [DEVICE_ID] bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [NEED_PREPROCESS] [DEVICE_ID]
``` ```
- `NEED_PREPROCESS` 表示数据是否需要预处理，取值范围为 'y' 或者 'n'。 - `NEED_PREPROCESS` 表示数据是否需要将推理中处理为mindrecord格式的原始数据集转换为二进制格式，取值范围为 'y' 或者 'n'。
- `DEVICE_ID` 可选，默认值为0。 - `DEVICE_ID` 可选，默认值为0。
### 结果 ### 结果