Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
曾经的那一瞬间
Models
提交
246e9c3b
M
Models
项目概览
曾经的那一瞬间
/
Models
大约 1 年 前同步成功
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
Models
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
246e9c3b
编写于
11月 08, 2022
作者:
H
Hongkun Yu
提交者:
A. Unique TensorFlower
11月 08, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Internal change
PiperOrigin-RevId: 487075916
上级
f8dbd5f1
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
17 addition
and
7 deletion
+17
-7
official/nlp/README.md
official/nlp/README.md
+5
-0
official/vision/README.md
official/vision/README.md
+5
-0
official/vision/examples/starter/README.md
official/vision/examples/starter/README.md
+7
-7
未找到文件。
official/nlp/README.md
浏览文件 @
246e9c3b
...
...
@@ -64,3 +64,8 @@ details.
We provide a large collection of baselines and checkpoints for NLP pre-trained
models. Please see
[
docs/pretrained_models.md
](
docs/pretrained_models.md
)
for
more details.
## More Documentations
Please read through the model training tutorials and references in the
[
docs/ folder
](
docs/README.md
)
.
official/vision/README.md
浏览文件 @
246e9c3b
...
...
@@ -293,3 +293,8 @@ training features including:
| MoViNet-A4-Base | 80 x 3 | 83.48 | 96.16 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/projects/movinet/configs/yaml/movinet_a4_k600_8x8.yaml
)
|
| MoViNet-A5-Base | 120 x 2 | 84.27 | 96.39 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/projects/movinet/configs/yaml/movinet_a5_k600_8x8.yaml
)
|
</details>
## More Documentations
Please read through the references in the
[
examples/starter
](
examples/starter
)
.
official/vision/examples/starter/README.md
浏览文件 @
246e9c3b
...
...
@@ -166,10 +166,10 @@ You can see in this file we import all our custom components:
```
python
# pylint: disable=unused-import
from
official.common
import
registry_imports
from
official.vision.
beta.projects.example
import
example_config
from
official.vision.
beta.projects.example
import
example_input
from
official.vision.
beta.projects.example
import
example_model
from
official.vision.
beta.projects.example
import
example_task
from
official.vision.
examples.starter
import
example_config
from
official.vision.
examples.starter
import
example_input
from
official.vision.
examples.starter
import
example_model
from
official.vision.
examples.starter
import
example_task
```
## Training
...
...
@@ -179,14 +179,14 @@ You can create your own trainer by branching from our core
Just make sure you import the registry like this:
```
python
from
official.vision.
beta.projects.example
import
registry_imports
# pylint: disable=unused-import
from
official.vision.
examples.starter
import
registry_imports
# pylint: disable=unused-import
```
You can run training locally for testing purpose:
```
bash
# Assume you are under official/vision/
project
s.
python3
example
/train.py
\
# Assume you are under official/vision/
example
s.
python3
starter
/train.py
\
--experiment
=
tf_vision_example_experiment
\
--config_file
=
${
PWD
}
/example/example_config_local.yaml
\
--mode
=
train
\
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录