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
c0cf58e6
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
c0cf58e6
编写于
7月 27, 2017
作者:
D
Derek Chow
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Update object_detection docs.
上级
7dde2e2f
变更
6
隐藏空白更改
内联
并排
Showing
6 changed file
with
17 addition
and
15 deletion
+17
-15
object_detection/g3doc/configuring_jobs.md
object_detection/g3doc/configuring_jobs.md
+3
-3
object_detection/g3doc/installation.md
object_detection/g3doc/installation.md
+1
-1
object_detection/g3doc/preparing_inputs.md
object_detection/g3doc/preparing_inputs.md
+3
-4
object_detection/g3doc/running_locally.md
object_detection/g3doc/running_locally.md
+2
-2
object_detection/g3doc/running_notebook.md
object_detection/g3doc/running_notebook.md
+2
-2
object_detection/g3doc/running_pets.md
object_detection/g3doc/running_pets.md
+6
-3
未找到文件。
object_detection/g3doc/configuring_jobs.md
浏览文件 @
c0cf58e6
...
...
@@ -157,6 +157,6 @@ number of workers, gpu type).
## Configuring the Evaluator
Currently evaluation is fixed to generating metrics as defined by the PASCAL
VOC challenge. The parameters for
`eval_config`
are set to reasonable defaults
and
typically do not need to be configured.
Currently evaluation is fixed to generating metrics as defined by the PASCAL
VOC
challenge. The parameters for
`eval_config`
are set to reasonable defaults and
typically do not need to be configured.
object_detection/g3doc/installation.md
浏览文件 @
c0cf58e6
...
...
@@ -74,6 +74,6 @@ to avoid running this manually, you can add it as a new line to the end of your
You can test that you have correctly installed the Tensorflow Object Detection
\
API by running the following command:
```
bash
```
bash
python object_detection/builders/model_builder_test.py
```
object_detection/g3doc/preparing_inputs.md
浏览文件 @
c0cf58e6
...
...
@@ -34,10 +34,9 @@ The label map for the PASCAL VOC data set can be found at
## Generating the Oxford-IIIT Pet TFRecord files.
The Oxford-IIIT Pet data set is located on
[
their website
](
http://www.robots.ox.ac.uk/~vgg/data/pets/
)
.
To download, extract and convert it to TFRecrods, run the following commands
below:
The Oxford-IIIT Pet data set is located
[
here
](
http://www.robots.ox.ac.uk/~vgg/data/pets/
)
. To download, extract and
convert it to TFRecrods, run the following commands below:
```
bash
# From tensorflow/models
...
...
object_detection/g3doc/running_locally.md
浏览文件 @
c0cf58e6
...
...
@@ -77,5 +77,5 @@ tensorboard --logdir=${PATH_TO_MODEL_DIRECTORY}
```
where
`${PATH_TO_MODEL_DIRECTORY}`
points to the directory that contains the
train and eval directories. Please note it may take Tensorboard a couple
minutes
to populate with data.
train and eval directories. Please note it may take Tensorboard a couple
minutes
to populate with data.
object_detection/g3doc/running_notebook.md
浏览文件 @
c0cf58e6
...
...
@@ -11,5 +11,5 @@ jupyter notebook
```
The notebook should open in your favorite web browser. Click the
[
`object_detection_tutorial.ipynb`
](
../object_detection_tutorial.ipynb
)
link
to
open the demo.
[
`object_detection_tutorial.ipynb`
](
../object_detection_tutorial.ipynb
)
link
to
open the demo.
object_detection/g3doc/running_pets.md
浏览文件 @
c0cf58e6
...
...
@@ -89,8 +89,8 @@ python object_detection/create_pet_tf_record.py \
Note: It is normal to see some warnings when running this script. You may ignore
them.
Two TFRecord files named
`pet_train.record`
and
`pet_val.record`
should be
generated
in the
`tensorflow/models`
directory.
Two TFRecord files named
`pet_train.record`
and
`pet_val.record`
should be
generated
in the
`tensorflow/models`
directory.
Now that the data has been generated, we'll need to upload it to Google Cloud
Storage so the data can be accessed by ML Engine. Run the following command to
...
...
@@ -269,7 +269,10 @@ Note: It takes roughly 10 minutes for a job to get started on ML Engine, and
roughly an hour for the system to evaluate the validation dataset. It may take
some time to populate the dashboards. If you do not see any entries after half
an hour, check the logs from the
[
ML Engine
Dashboard
](
https://console.cloud.google.com/mlengine/jobs
)
.
Dashboard
](
https://console.cloud.google.com/mlengine/jobs
)
. Note that by default
the training jobs are configured to go for much longer than is necessary for
convergence. To save money, we recommend killing your jobs once you've seen
that they've converged.
## Exporting the Tensorflow Graph
...
...
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