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
Greenplum
Pytorch Widedeep
提交
7be73d04
P
Pytorch Widedeep
项目概览
Greenplum
/
Pytorch Widedeep
10 个月 前同步成功
通知
9
Star
1
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
P
Pytorch Widedeep
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
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
7be73d04
编写于
6月 25, 2021
作者:
J
jrzaurin
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Adjusted docs and README. Bump to version 1
上级
0070c739
变更
8
隐藏空白更改
内联
并排
Showing
8 changed file
with
37 addition
and
35 deletion
+37
-35
.travis.yml
.travis.yml
+1
-0
README.md
README.md
+13
-14
VERSION
VERSION
+1
-1
docs/examples.rst
docs/examples.rst
+1
-0
docs/index.rst
docs/index.rst
+7
-5
pypi_README.md
pypi_README.md
+12
-13
pytorch_widedeep/preprocessing/tab_preprocessor.py
pytorch_widedeep/preprocessing/tab_preprocessor.py
+1
-1
pytorch_widedeep/version.py
pytorch_widedeep/version.py
+1
-1
未找到文件。
.travis.yml
浏览文件 @
7be73d04
...
@@ -4,6 +4,7 @@ python:
...
@@ -4,6 +4,7 @@ python:
-
"
3.6"
-
"
3.6"
-
"
3.7"
-
"
3.7"
-
"
3.8"
-
"
3.8"
-
"
3.9"
matrix
:
matrix
:
fast_finish
:
true
fast_finish
:
true
include
:
include
:
...
...
README.md
浏览文件 @
7be73d04
...
@@ -9,7 +9,7 @@
...
@@ -9,7 +9,7 @@
[
![Maintenance
](
https://img.shields.io/badge/Maintained%3F-yes-green.svg
)
](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
[
![Maintenance
](
https://img.shields.io/badge/Maintained%3F-yes-green.svg
)
](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
[
![contributions welcome
](
https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
)
](https://github.com/jrzaurin/pytorch-widedeep/issues)
[
![contributions welcome
](
https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
)
](https://github.com/jrzaurin/pytorch-widedeep/issues)
[
![codecov
](
https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg
)
](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
[
![codecov
](
https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg
)
](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
[
![Python 3.6 3.7 3.8
](
https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8
-blue.svg
)
](https://www.python.org/)
[
![Python 3.6 3.7 3.8
3.9
](
https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9
-blue.svg
)
](https://www.python.org/)
# pytorch-widedeep
# pytorch-widedeep
...
@@ -24,8 +24,7 @@ using wide and deep models.
...
@@ -24,8 +24,7 @@ using wide and deep models.
### Introduction
### Introduction
`pytorch-widedeep`
is based on Google's Wide and Deep Algorithm,
[
Wide & Deep
``pytorch-widedeep``
is based on Google's
[
Wide and Deep Algorithm
](
https://arxiv.org/abs/1606.07792
)
Learning for Recommender Systems
](
https://arxiv.org/abs/1606.07792
)
.
In general terms,
`pytorch-widedeep`
is a package to use deep learning with
In general terms,
`pytorch-widedeep`
is a package to use deep learning with
tabular data. In particular, is intended to facilitate the combination of text
tabular data. In particular, is intended to facilitate the combination of text
...
@@ -86,7 +85,7 @@ It is important to emphasize that **each individual component, `wide`,
...
@@ -86,7 +85,7 @@ It is important to emphasize that **each individual component, `wide`,
isolation. For example, one could use only
`wide`
, which is in simply a linear
isolation. For example, one could use only
`wide`
, which is in simply a linear
model. In fact, one of the most interesting functionalities
model. In fact, one of the most interesting functionalities
in
``pytorch-widedeep``
is the
``deeptabular``
component. Currently,
in
``pytorch-widedeep``
is the
``deeptabular``
component. Currently,
``pytorch-widedeep``
offers
3
models for that component:
``pytorch-widedeep``
offers
4
models for that component:
1.
``TabMlp``
: this is almost identical to the
[
tabular
1.
``TabMlp``
: this is almost identical to the
[
tabular
model
](
https://docs.fast.ai/tutorial.tabular.html
)
in the fantastic
model
](
https://docs.fast.ai/tutorial.tabular.html
)
in the fantastic
...
@@ -144,20 +143,20 @@ cd pytorch-widedeep
...
@@ -144,20 +143,20 @@ cd pytorch-widedeep
pip
install
-e
.
pip
install
-e
.
```
```
**Important note for Mac users**
: at the time of writing (
Feb-2021) the latest
**Important note for Mac users**
: at the time of writing (
June-2021) the
`torch`
release is
`1.7.1`
. This release has some
latest
`torch`
release is
`1.9`
. Some past
[
issues
](
https://stackoverflow.com/questions/64772335/pytorch-w-parallelnative-cpp206
)
[
issues
](
https://stackoverflow.com/questions/64772335/pytorch-w-parallelnative-cpp206
)
when running on Mac
and the data-loaders will not run in parallel. In
when running on Mac
, present in previous versions, persist on this release and
addition, since
`python 3.8`
,
[
the `multiprocessing` library start method
the data-loaders will not run in parallel. In addition, since
`python 3.8`
,
changed from `'fork'` to
[
the `multiprocessing` library start method
changed from `'fork'` to
`'spawn'`
](
https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
)
.
`'spawn'`
](
https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
)
.
This also affects the data-loaders (for any
`torch`
version) and they will
not
This also affects the data-loaders (for any
`torch`
version) and they will
run in parallel. Therefore, for Mac users I recommend using
`python 3.6`
or
not run in parallel. Therefore, for Mac users I recommend using
`python 3.6`
`3.7`
and
`torch <= 1.6`
(with the corresponding, consistent version of
or
`3.7`
and
`torch <= 1.6`
(with the corresponding, consistent version of
`torchvision`
, e.g.
`0.7.0`
for
`torch 1.6`
). I do not want to force this
`torchvision`
, e.g.
`0.7.0`
for
`torch 1.6`
). I do not want to force this
versioning in the
`setup.py`
file since I expect that all these issues are
versioning in the
`setup.py`
file since I expect that all these issues are
fixed in the future. Therefore, after installing
`pytorch-widedeep`
via pip
or
fixed in the future. Therefore, after installing
`pytorch-widedeep`
via pip
directly from github, downgrade
`torch`
and
`torchvision`
manually:
or
directly from github, downgrade
`torch`
and
`torchvision`
manually:
```
bash
```
bash
pip
install
pytorch-widedeep
pip
install
pytorch-widedeep
...
...
VERSION
浏览文件 @
7be73d04
0.4.8
1.0.0
\ No newline at end of file
\ No newline at end of file
docs/examples.rst
浏览文件 @
7be73d04
...
@@ -13,3 +13,4 @@ them to address different problems
...
@@ -13,3 +13,4 @@ them to address different problems
* `Regression with Images and Text <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/05_Regression_with_Images_and_Text.ipynb>`__
* `Regression with Images and Text <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/05_Regression_with_Images_and_Text.ipynb>`__
* `FineTune routines <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/06_FineTune_and_WarmUp_Model_Components.ipynb>`__
* `FineTune routines <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/06_FineTune_and_WarmUp_Model_Components.ipynb>`__
* `Custom Components <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/07_Custom_Components.ipynb>`__
* `Custom Components <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/07_Custom_Components.ipynb>`__
* `Save and Load Model and Artifacts <https://github.com/jrzaurin/pytorch-widedeep/blob/master/examples/08_save_and_load_model_and_artifacts.ipynb>`__
docs/index.rst
浏览文件 @
7be73d04
...
@@ -90,7 +90,7 @@ deeptabular, deeptext and deepimage, can be used independently** and in
...
@@ -90,7 +90,7 @@ deeptabular, deeptext and deepimage, can be used independently** and in
isolation. For example, one could use only ``wide``, which is in simply a
isolation. For example, one could use only ``wide``, which is in simply a
linear model. In fact, one of the most interesting offerings of
linear model. In fact, one of the most interesting offerings of
``pytorch-widedeep`` is the ``deeptabular`` component. Currently,
``pytorch-widedeep`` is the ``deeptabular`` component. Currently,
``pytorch-widedeep`` offers
3
models for that component:
``pytorch-widedeep`` offers
4
models for that component:
1. ``TabMlp``: this is almost identical to the `tabular
1. ``TabMlp``: this is almost identical to the `tabular
model <https://docs.fast.ai/tutorial.tabular.html>`_ in the fantastic
model <https://docs.fast.ai/tutorial.tabular.html>`_ in the fantastic
...
@@ -101,12 +101,14 @@ features, and passed then through a MLP.
...
@@ -101,12 +101,14 @@ features, and passed then through a MLP.
2. ``TabRenset``: This is similar to the previous model but the embeddings are
2. ``TabRenset``: This is similar to the previous model but the embeddings are
passed through a series of ResNet blocks built with dense layers.
passed through a series of ResNet blocks built with dense layers.
3. ``TabTransformer``: Details on the TabTransformer can be found in:
3. ``Tabnet``: Details on TabNet can be found in: `TabNet: Attentive
`TabTransformer: Tabular Data Modeling Using Contextual
Interpretable Tabular Learning <https://arxiv.org/abs/1908.07442>`_.
Embeddings <https://arxiv.org/pdf/2012.06678.pdf>`_.
4. ``TabTransformer``: Details on the TabTransformer can be found in:
`TabTransformer: Tabular Data Modeling Using Contextual Embeddings
<https://arxiv.org/pdf/2012.06678.pdf>`_.
For details on these
3
models and their options please see the examples in the
For details on these
4
models and their options please see the examples in the
Examples folder and the documentation.
Examples folder and the documentation.
Finally, while I recommend using the ``wide`` and ``deeptabular`` models in
Finally, while I recommend using the ``wide`` and ``deeptabular`` models in
...
...
pypi_README.md
浏览文件 @
7be73d04
...
@@ -4,7 +4,7 @@
...
@@ -4,7 +4,7 @@
[
![Maintenance
](
https://img.shields.io/badge/Maintained%3F-yes-green.svg
)
](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
[
![Maintenance
](
https://img.shields.io/badge/Maintained%3F-yes-green.svg
)
](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
[
![contributions welcome
](
https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
)
](https://github.com/jrzaurin/pytorch-widedeep/issues)
[
![contributions welcome
](
https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat
)
](https://github.com/jrzaurin/pytorch-widedeep/issues)
[
![codecov
](
https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg
)
](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
[
![codecov
](
https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg
)
](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
[
![Python 3.6 3.7 3.8
](
https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8
-blue.svg
)
](https://www.python.org/)
[
![Python 3.6 3.7 3.8
3.9
](
https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9
-blue.svg
)
](https://www.python.org/)
# pytorch-widedeep
# pytorch-widedeep
...
@@ -19,8 +19,7 @@ using wide and deep models.
...
@@ -19,8 +19,7 @@ using wide and deep models.
### Introduction
### Introduction
`pytorch-widedeep`
is based on Google's Wide and Deep Algorithm,
[
Wide & Deep
``pytorch-widedeep``
is based on Google's
[
Wide and Deep Algorithm
](
https://arxiv.org/abs/1606.07792
)
Learning for Recommender Systems
](
https://arxiv.org/abs/1606.07792
)
.
In general terms,
`pytorch-widedeep`
is a package to use deep learning with
In general terms,
`pytorch-widedeep`
is a package to use deep learning with
tabular data. In particular, is intended to facilitate the combination of text
tabular data. In particular, is intended to facilitate the combination of text
...
@@ -56,20 +55,20 @@ cd pytorch-widedeep
...
@@ -56,20 +55,20 @@ cd pytorch-widedeep
pip
install
-e
.
pip
install
-e
.
```
```
**Important note for Mac users**
: at the time of writing (
Dec-2020) the latest
**Important note for Mac users**
: at the time of writing (
June-2021) the
`torch`
release is
`1.7`
. This release has some
latest
`torch`
release is
`1.9`
. Some past
[
issues
](
https://stackoverflow.com/questions/64772335/pytorch-w-parallelnative-cpp206
)
[
issues
](
https://stackoverflow.com/questions/64772335/pytorch-w-parallelnative-cpp206
)
when running on Mac
and the data-loaders will not run in parallel. In
when running on Mac
, present in previous versions, persist on this release and
addition, since
`python 3.8`
,
[
the `multiprocessing` library start method
the data-loaders will not run in parallel. In addition, since
`python 3.8`
,
changed from `'fork'` to
[
the `multiprocessing` library start method
changed from `'fork'` to
`'spawn'`
](
https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
)
.
`'spawn'`
](
https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
)
.
This also affects the data-loaders (for any
`torch`
version) and they will
not
This also affects the data-loaders (for any
`torch`
version) and they will
run in parallel. Therefore, for Mac users I recommend using
`python 3.6`
or
not run in parallel. Therefore, for Mac users I recommend using
`python 3.6`
`3.7`
and
`torch <= 1.6`
(with the corresponding, consistent version of
or
`3.7`
and
`torch <= 1.6`
(with the corresponding, consistent version of
`torchvision`
, e.g.
`0.7.0`
for
`torch 1.6`
). I do not want to force this
`torchvision`
, e.g.
`0.7.0`
for
`torch 1.6`
). I do not want to force this
versioning in the
`setup.py`
file since I expect that all these issues are
versioning in the
`setup.py`
file since I expect that all these issues are
fixed in the future. Therefore, after installing
`pytorch-widedeep`
via pip
or
fixed in the future. Therefore, after installing
`pytorch-widedeep`
via pip
directly from github, downgrade
`torch`
and
`torchvision`
manually:
or
directly from github, downgrade
`torch`
and
`torchvision`
manually:
```
bash
```
bash
pip
install
pytorch-widedeep
pip
install
pytorch-widedeep
...
...
pytorch_widedeep/preprocessing/tab_preprocessor.py
浏览文件 @
7be73d04
...
@@ -36,7 +36,7 @@ class TabPreprocessor(BasePreprocessor):
...
@@ -36,7 +36,7 @@ class TabPreprocessor(BasePreprocessor):
the possibility of normalising the input continuous features via a
the possibility of normalising the input continuous features via a
``BatchNorm`` or a ``LayerNorm`` layer. see
``BatchNorm`` or a ``LayerNorm`` layer. see
:class:`pytorch_widedeep.models`
:class:`pytorch_widedeep.models`
auto_embed_dim: bool
auto_embed_dim: bool
, default = True
Boolean indicating whether the embedding dimensions will be
Boolean indicating whether the embedding dimensions will be
automatically defined via fastai's rule of thumb':
automatically defined via fastai's rule of thumb':
:math:`min(600, int(1.6 \times n_{cat}^{0.56}))`
:math:`min(600, int(1.6 \times n_{cat}^{0.56}))`
...
...
pytorch_widedeep/version.py
浏览文件 @
7be73d04
__version__
=
"
0.4.8
"
__version__
=
"
1.0.0
"
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