This website works better with JavaScript.
Home
Issues
Pull Requests
Milestones
AI流水线
Repositories
Datasets
Forum
实训
竞赛
大数据
AI开发
Register
Sign In
Huawei_Technology
/
mindspore
Not watched
Unwatch
Watch all
Watch but not notify
1
Star
0
Fork
0
Code
Releases
13
Wiki
evaluate
Activity
Issues
0
Pull Requests
0
Datasets
Model
Cloudbrain
HPC
Browse Source
!10948
modify maskrcnn readme,add description of bs and hard disk
From:
@yuzhenhua666
Reviewed-by: @oacjiewen,@wuxuejian Signed-off-by:
@wuxuejian
tags/v1.2.0-rc1
mindspore-ci-bot
Gitee
4 years ago
parent
f31dfa129a
1cd1eee46d
commit
1f5d895986
2 changed files
with
2 additions
and
1 deletions
Split View
Diff Options
Show Stats
Download Patch File
Download Diff File
+1
-0
model_zoo/official/cv/maskrcnn/README.md
+1
-1
model_zoo/official/cv/maskrcnn/README_CN.md
+ 1
- 0
model_zoo/official/cv/maskrcnn/README.md
View File
@@ -505,6 +505,7 @@ python export.py --ckpt_file [CKPT_PATH] --device_target [DEVICE_TARGET] --file_
### Usage
Before performing inference, the air file must bu exported by export script on the 910 environment.
Current batch_ Size can only be set to 1. The inference process needs about 600G hard disk space to save the reasoning results.
```shell
# Ascend310 inference
+ 1
- 1
model_zoo/official/cv/maskrcnn/README_CN.md
View File
@@ -439,7 +439,7 @@ python export.py --ckpt_file [CKPT_PATH] --device_target [DEVICE_TARGET] --file_
### 使用方法
在推理之前需要在昇腾910环境上完成模型的导出。
在推理之前需要在昇腾910环境上完成模型的导出。
目前推理只支持batch_size=1。推理过程需要占用大约600G的硬盘空间来保存推理的结果。
```shell
# Ascend310 推理
Write
Preview
Loading…
Cancel
Save