Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
2
221cb0332
Manage
Activity
Members
Labels
Plan
Issues
0
Issue boards
Milestones
Wiki
Code
Merge requests
0
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Summer2022
221cb0332
Commits
20b86dd2
Unverified
Commit
20b86dd2
authored
2 years ago
by
i-robot
Committed by
Gitee
2 years ago
Browse files
Options
Downloads
Plain Diff
!2499 fix pgan eval scale config
Merge pull request !2499 from Shawny/pgan
parents
c01e2a3b
da6a5f77
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
research/cv/PGAN/README_CN.md
+36
-2
36 additions, 2 deletions
research/cv/PGAN/README_CN.md
with
36 additions
and
2 deletions
research/cv/PGAN/README_CN.md
+
36
−
2
View file @
20b86dd2
...
...
@@ -149,13 +149,47 @@ CelebFaces Attributes Dataset (CelebA) 是一个大规模的人脸属性数据
-
在Ascend环境下生成图片
用户生成64张人脸图片
评估时选择已经生成好的检查点文件,作为参数传入测试脚本,对应参数为
`checkpoint_g`
(保存了生成器的checkpoint)
评估时选择已经生成好的检查点文件,作为参数传入测试脚本,对应参数为
`checkpoint_g`
(保存了生成器的checkpoint)
。请指定“AvG
**
.ckpt”进行推理。
```
bash
bash run_eval.sh /path/checkpoint 0
```
测试脚本执行完成后,用户进入当前目录下的
`img_eval/`
下查看生成的人脸图片。
默认推理配置为scale=128,如推理scale=64规格的图片,请将eval.py中的设置更改为
```
bash
scales
=
[
4, 8, 16, 32, 64]
depth
=
[
512, 512, 512, 512, 256]
```
如推理scale=32规格的图片,请将eval.py中的设置更改为
```
bash
scales
=
[
4, 8, 16, 32]
depth
=
[
512, 512, 512, 512]
```
如推理scale=16规格的图片,请将eval.py中的设置更改为
```
bash
scales
=
[
4, 8, 16]
depth
=
[
512, 512, 512]
```
如推理scale=8规格的图片,请将eval.py中的设置更改为
```
bash
scales
=
[
4, 8]
depth
=
[
512, 512]
```
如推理scale=4规格的图片,请将eval.py中的设置更改为
```
bash
scales
=
[
4]
depth
=
[
512]
```
## 推理过程
...
...
@@ -165,7 +199,7 @@ CelebFaces Attributes Dataset (CelebA) 是一个大规模的人脸属性数据
python export.py
--checkpoint_g
[
GENERATOR_CKPT_NAME]
--device_id
[
DEVICE_ID]
```
脚本会在当前目录下生成对应的MINDIR文件。
默认使用scale=128生成的ckpt文件进行导出,
脚本会在当前目录下生成对应的MINDIR文件。
### 在Ascend310执行推理
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment