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
wux_labs
Tensorflow
提交
f9cc62cf
T
Tensorflow
项目概览
wux_labs
/
Tensorflow
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
T
Tensorflow
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
f9cc62cf
编写于
6月 03, 2016
作者:
A
A. Unique TensorFlower
提交者:
TensorFlower Gardener
6月 03, 2016
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Update generated Python Op docs.
Change: 123983886
上级
b7dd0381
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
80 addition
and
0 deletion
+80
-0
tensorflow/g3doc/api_docs/python/array_ops.md
tensorflow/g3doc/api_docs/python/array_ops.md
+41
-0
tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.extract_image_patches.md
.../functions_and_classes/shard4/tf.extract_image_patches.md
+38
-0
tensorflow/g3doc/api_docs/python/index.md
tensorflow/g3doc/api_docs/python/index.md
+1
-0
未找到文件。
tensorflow/g3doc/api_docs/python/array_ops.md
浏览文件 @
f9cc62cf
...
...
@@ -936,6 +936,47 @@ tf.transpose(x, perm=[0, 2, 1]) ==> [[[1 4]
A transposed
`Tensor`
.
- - -
### `tf.extract_image_patches(images, padding, ksizes=None, strides=None, rates=None, name=None)` {#extract_image_patches}
Extract
`patches`
from
`images`
and puth them in the "depth" output dimension.
##### Args:
*
<b>
`images`
</b>
: A
`Tensor`
. Must be one of the following types:
`float32`
,
`float64`
,
`int32`
,
`int64`
,
`uint8`
,
`int16`
,
`int8`
,
`uint16`
,
`half`
.
4-D Tensor with shape
`[batch, in_rows, in_cols, depth]`
.
*
<b>
`padding`
</b>
: A
`string`
from:
`"SAME", "VALID"`
.
The type of padding algorithm to use.
We specify the size-related attributes as:
ksizes = [1, ksize_rows, ksize_cols, 1]
strides = [1, strides_rows, strides_cols, 1]
rates = [1, rates_rows, rates_cols, 1]
*
<b>
`ksizes`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
The size of the sliding window for each dimension of
`images`
.
*
<b>
`strides`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
1-D of length 4. How far the centers of two consecutive patches are in
the images. Must be:
`[1, stride_rows, stride_cols, 1]`
.
*
<b>
`rates`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
1-D of length 4. Must be:
`[1, rate_rows, rate_cols, 1]`
. This is the
input stride, specifying how far two consecutive patch samples are in the
input. Equivalent to extracting patches with
`patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1), followed by
subsampling them spatially by a factor of `
rates
`.
* <b>`
name
`</b>: A name for the operation (optional).
##### Returns:
A `
Tensor
`. Has the same type as `
images
`.
4-D Tensor with shape `
[batch, out_rows, out_cols, ksize_rows
*
ksize_cols
*
depth]
` containing image patches with size
`
ksize_rows x ksize_cols x depth
` vectorized in the "depth" dimension.
- - -
### `
tf.space_to_batch(input, paddings, block_size, name=None)
` {#space_to_batch}
...
...
tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.extract_image_patches.md
0 → 100644
浏览文件 @
f9cc62cf
### `tf.extract_image_patches(images, padding, ksizes=None, strides=None, rates=None, name=None)` {#extract_image_patches}
Extract
`patches`
from
`images`
and puth them in the "depth" output dimension.
##### Args:
*
<b>
`images`
</b>
: A
`Tensor`
. Must be one of the following types:
`float32`
,
`float64`
,
`int32`
,
`int64`
,
`uint8`
,
`int16`
,
`int8`
,
`uint16`
,
`half`
.
4-D Tensor with shape
`[batch, in_rows, in_cols, depth]`
.
*
<b>
`padding`
</b>
: A
`string`
from:
`"SAME", "VALID"`
.
The type of padding algorithm to use.
We specify the size-related attributes as:
ksizes = [1, ksize_rows, ksize_cols, 1]
strides = [1, strides_rows, strides_cols, 1]
rates = [1, rates_rows, rates_cols, 1]
*
<b>
`ksizes`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
The size of the sliding window for each dimension of
`images`
.
*
<b>
`strides`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
1-D of length 4. How far the centers of two consecutive patches are in
the images. Must be:
`[1, stride_rows, stride_cols, 1]`
.
*
<b>
`rates`
</b>
: An optional list of
`ints`
. Defaults to
`[]`
.
1-D of length 4. Must be:
`[1, rate_rows, rate_cols, 1]`
. This is the
input stride, specifying how far two consecutive patch samples are in the
input. Equivalent to extracting patches with
`patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1), followed by
subsampling them spatially by a factor of `
rates
`.
* <b>`
name
`</b>: A name for the operation (optional).
##### Returns:
A `
Tensor
`. Has the same type as `
images
`.
4-D Tensor with shape `
[batch, out_rows, out_cols, ksize_rows
*
ksize_cols
*
depth]
` containing image patches with size
`
ksize_rows x ksize_cols x depth
`
vectorized in the "depth" dimension.
tensorflow/g3doc/api_docs/python/index.md
浏览文件 @
f9cc62cf
...
...
@@ -121,6 +121,7 @@
*
[
`dynamic_partition`
](
../../api_docs/python/array_ops.md#dynamic_partition
)
*
[
`dynamic_stitch`
](
../../api_docs/python/array_ops.md#dynamic_stitch
)
*
[
`expand_dims`
](
../../api_docs/python/array_ops.md#expand_dims
)
*
[
`extract_image_patches`
](
../../api_docs/python/array_ops.md#extract_image_patches
)
*
[
`gather`
](
../../api_docs/python/array_ops.md#gather
)
*
[
`gather_nd`
](
../../api_docs/python/array_ops.md#gather_nd
)
*
[
`one_hot`
](
../../api_docs/python/array_ops.md#one_hot
)
...
...
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