Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
47 commits
Select commit Hold shift + click to select a range
4686391
fix bug of autoint model demo config
yangxudong Dec 20, 2024
4011d71
Merge branch 'master' into daily_bug_fix
yangxudong Dec 25, 2024
a23298b
fix bug of wrong demo model configs
yangxudong Dec 25, 2024
9e131bc
Merge branch 'master' into daily_bug_fix
yangxudong Dec 31, 2024
7f5ddad
fix bug of undefined flags of easyrec tools run with DeepRec
yangxudong Dec 31, 2024
74b1edc
fix bug
yangxudong Jan 3, 2025
8ffbc29
fix bug
yangxudong Jan 3, 2025
3f97db9
fix bug
yangxudong Jan 3, 2025
c7d7a0d
fix bug
yangxudong Jan 3, 2025
eed8283
fix bug
yangxudong Jan 6, 2025
d7a1860
Build docker (#515)
yanzhen1233 Jan 16, 2025
179cfa3
merge from master
yangxudong Jan 17, 2025
1f81f2b
fix bug of autoint model demo config
yangxudong Dec 20, 2024
c00d33e
fix bug of wrong demo model configs
yangxudong Dec 25, 2024
bf983d4
Merge branch 'master' into daily_bug_fix
yangxudong Jan 17, 2025
8317df7
merge from master
yangxudong Jan 17, 2025
9cd8ca1
merge from master
yangxudong Jan 17, 2025
cd9fdcc
merge from master
yangxudong Jan 17, 2025
8935776
merge from master
yangxudong Jan 17, 2025
e6dadc3
Merge branch 'master' into daily_bug_fix
yangxudong Jan 23, 2025
fdffb37
fix bug of SeqAugment layer
yangxudong Jan 23, 2025
a62c34b
add compacity for windows users
yangxudong Jan 23, 2025
2e80cf0
Merge branch 'master' into daily_bug_fix
yangxudong Feb 18, 2025
0385791
prevant to include wrong tensorflow_probability version
yangxudong Feb 18, 2025
fa41d55
Merge branch 'master' into daily_bug_fix
yangxudong May 13, 2025
8f13ba4
add some examples for backbone components
yangxudong May 13, 2025
cc7ee5d
Merge branch 'master' into daily_bug_fix
yangxudong May 28, 2025
55d6a87
fix bug of gfile compatibility
yangxudong May 28, 2025
a3efa85
fix bug of gfile compatibility
yangxudong May 28, 2025
20a391b
fix bug of gfile compatibility
yangxudong May 28, 2025
38fa46b
fix bug of gfile compatibility
yangxudong May 29, 2025
f7a62e2
fix bug of gfile compatibility
yangxudong May 29, 2025
8e8e3c7
fix bug of gfile compatibility
yangxudong May 29, 2025
dcc0f4a
fix bug of gfile compatibility
yangxudong May 29, 2025
cf6a4c5
fix bug of gfile compatibility
yangxudong May 29, 2025
d6bd2b6
fix bug of gfile compatibility
yangxudong May 29, 2025
cb37281
fix bug of gfile compatibility
yangxudong Jun 3, 2025
90d81c9
fix bug of gfile compatibility
yangxudong Jun 4, 2025
5e1d8e9
Merge branch 'master' into daily_bug_fix
yangxudong Jun 24, 2025
5d61a09
update FG document
yangxudong Sep 10, 2025
d7f0d77
update FG document
yangxudong Sep 10, 2025
37123ff
update FG document
yangxudong Sep 10, 2025
29ee292
update FG document
yangxudong Sep 11, 2025
7897820
update FG document
yangxudong Sep 11, 2025
07cf59b
update FG document
yangxudong Sep 11, 2025
f4c138d
update FG document
yangxudong Sep 12, 2025
dc5aa67
fix fg input size check
yangxudong Sep 24, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 36 additions & 0 deletions docker/Dockerfile_paitf115
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
FROM dsw-registry.cn-shanghai.cr.aliyuncs.com/pai/tensorflow-training:1.15PAI-cpu-py36-ubuntu18.04

COPY docker/sources_18.04.list /etc/apt/sources.list

# necessary for later commands to take effect
RUN md5sum /etc/apt/sources.list

RUN apt-get update
RUN apt-get install apt-utils inetutils-ping wget curl telnet vim strace libpq-dev curl libsasl2-dev gcc g++ unzip openjdk-8-jdk -y

RUN mkdir /EasyRec
COPY requirements /EasyRec/requirements
COPY requirements.txt /EasyRec/
COPY easy_rec /EasyRec/easy_rec/
COPY setup.cfg /EasyRec/
COPY setup.py /EasyRec/
COPY MANIFEST.in /EasyRec/
COPY README.md /EasyRec/
COPY scripts /EasyRec/scripts

RUN curl "http://easyrec.oss-cn-beijing.aliyuncs.com/tools/odpscmd_public_0.45.0.zip" -o /EasyRec/odpscmd_public.zip
RUN mkdir /usr/local/odps_clt/ && cd /usr/local/odps_clt/ && unzip /EasyRec/odpscmd_public.zip
RUN ln -s /usr/local/odps_clt/bin/odpscmd /usr/local/bin/odpscmd
RUN pip3 install --upgrade pip
RUN pip3 install pystack-debugger idna kafka-python -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install -r /EasyRec/requirements/runtime.txt
RUN pip3 install -r /EasyRec/requirements/extra.txt -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install http://easyrec.oss-cn-beijing.aliyuncs.com/3rdparty/graphlearn-1.1.0-cp36-cp36m-linux_x86_64.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install http://easyrec.oss-cn-beijing.aliyuncs.com/releases/pai_automl-0.0.1rc1-py3-none-any.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install https://easyrec.oss-cn-beijing.aliyuncs.com/3rdparty/common_io-0.4.2%2Btunnel-py2.py3-none-any.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install tensorflow_probability==0.8 -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN cd /EasyRec && pip install .
RUN rm -rf /EasyRec
RUN python -c "import easy_rec; easy_rec.help(); import pyhive; import datahub; import kafka"

COPY docker/hadoop_env.sh /opt/hadoop_env.sh
36 changes: 36 additions & 0 deletions docker/Dockerfile_tf211
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
FROM dsw-registry.cn-shanghai.cr.aliyuncs.com/pai/tensorflow:2.11-cpu-py39-ubuntu20.04-1
COPY docker/sources_20.04.list /etc/apt/sources.list

# necessary for later commands to take effect
RUN md5sum /etc/apt/sources.list

RUN apt-get update
RUN apt-get install apt-utils inetutils-ping wget curl telnet vim strace libpq-dev curl libsasl2-dev gcc g++ unzip openjdk-8-jdk -y

RUN mkdir /EasyRec
COPY requirements /EasyRec/requirements
COPY requirements.txt /EasyRec/
COPY easy_rec /EasyRec/easy_rec/
COPY setup.cfg /EasyRec/
COPY setup.py /EasyRec/
COPY MANIFEST.in /EasyRec/
COPY README.md /EasyRec/
COPY scripts /EasyRec/scripts

RUN curl "http://easyrec.oss-cn-beijing.aliyuncs.com/tools/odpscmd_public_0.45.0.zip" -o /EasyRec/odpscmd_public.zip
RUN mkdir /usr/local/odps_clt/ && cd /usr/local/odps_clt/ && unzip /EasyRec/odpscmd_public.zip
RUN ln -s /usr/local/odps_clt/bin/odpscmd /usr/local/bin/odpscmd
RUN python -m pip install --upgrade pip
RUN pip3 install pystack-debugger idna kafka-python -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install -r /EasyRec/requirements/runtime.txt -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install -r /EasyRec/requirements/extra.txt -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install https://tzrec.oss-cn-beijing.aliyuncs.com/third_party/graphlearn-1.2.0-cp39-cp39-linux_x86_64.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
# RUN pip3 install http://easyrec.oss-cn-beijing.aliyuncs.com/releases/pai_automl-0.0.1rc1-py3-none-any.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN pip3 install tensorflow_probability==0.19.0 -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
#RUN pip3 install encodings
RUN pip3 install https://easyrec.oss-cn-beijing.aliyuncs.com/3rdparty/common_io-0.4.j2%2Btunnel-py2.py3-none-any.whl -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com
RUN cd /EasyRec && pip install .
RUN rm -rf /EasyRec
# RUN python -c "import easy_rec; easy_rec.help(); import pyhive; import datahub; import kafka"

COPY docker/hadoop_env.sh /opt/hadoop_env.sh
1 change: 1 addition & 0 deletions docs/images/other/fg.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
21 changes: 0 additions & 21 deletions docs/source/feature/feature.rst
Original file line number Diff line number Diff line change
Expand Up @@ -462,27 +462,6 @@ ExprFeature:表达式特征
- 当前版本未定义"&","|"的符号优先级,建议使用括号保证优先级。
- customized normalization: "tf.math.log1p(user_age) / 10.0"

EmbeddingVariable
----------------------------------------------------------------
Key Value Hash, 减少hash冲突, 支持特征准入和特征淘汰。

.. code:: protobuf

model_config {
model_class: "MultiTower"
...
ev_params {
filter_freq: 2
}
}
- 配置方式:
- feature_config单独配置ev_params
- model_config里面统一配置ev_params

- ev_params : EVParams
- filter_freq: 频次过滤, 低频特征噪声大,过滤噪声让模型更鲁棒
- steps_to_live: 特征淘汰, 淘汰过期特征,防止模型过大
- Note: 仅在安装PAI-TF/DeepRec时可用

特征选择
----------------------------------------------------------------
Expand Down
Loading