Deepctr

Latest version: v0.9.3

Safety actively analyzes 629532 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 5 of 8

0.5.0

Change Log
Major Features and Improvements

- Refactor inputs module,now you can input different features to linear part and dnn part of the models.
- Dense value inputs are concated with the inputs of dnn instead of embed into dense vectors.
- **previous versions of the code require modification to work properly**,please refer [new examples](https://deepctr-doc.readthedocs.io/en/latest/Examples.html) to update your codes.

0.4.1

Change Log
Major Features and Improvements

- Add [DSIN(Deep Session Interest Network)](https://deepctr-doc.readthedocs.io/en/latest/Features.html#dsin-deep-session-interest-network)
[paper](https://arxiv.org/abs/1905.06482) [code](https://github.com/shenweichen/DSIN)
- Refactor layers

0.4.0

Change Log
Major Features and Improvements
- **Previous versions of the code require a little modification to work properly**
- Support feature hashing on the fly in training and inference process [example](https://deepctr-doc.readthedocs.io/en/latest/Examples.html#classification-criteo-with-feature-hashing-on-the-fly)
- Add python2.7 support
- Refactor methods in `input_embedding.py`
- Refactor layers and models

API changes
- `deepctr.utils.SingleFeat`and `deepctr.utisl.VarlenFeat` add new arguments to support feature hashing
- `deepctr.core.MLP` to `deepctr.core.DNN`
- arguments of all models and layers changes

|v0.3.4|v0.4.0|
|--|--|
|l2_reg_deep|l2_reg_dnn|
|activation|dnn_activation|
|keep_prob|dnn_dropout|
|hidden_size|dnn_hidden_units|
|use_bn|dnn_use_bn|
|final_activation|task|

0.3.4

Change Log
Major Features and Improvements

- Add [FGCNN(Feature Generation by Convolutional Neural Network)](https://deepctr-doc.readthedocs.io/en/latest/Features.html#fgcnn-feature-generation-by-convolutional-neural-network)[CCPM&FGCNN:使用CNN进行特征生成的CTR预测模型](https://zhuanlan.zhihu.com/p/64015347)
- Add `FGCNNLayer` in `deepctr.layers.interaction` [doc](https://deepctr-doc.readthedocs.io/en/latest/deepctr.layers.interaction.html#deepctr.layers.interaction.FGCNNLayer)
- Now we can use deepctr under `tensorflow 1.13`, but there may be some compatibility issues.

0.3.3

Change Log
Major Features and Improvements

- Add [CCPM(Convolutional Click Prediction Model)](https://deepctr-doc.readthedocs.io/en/latest/Features.html#ccpm-convolutional-click-prediction-model)
- Add `KMaxPooling` in `deepctr.layers.sequence` [doc](https://deepctr-doc.readthedocs.io/en/latest/deepctr.layers.sequence.html#deepctr.layers.sequence.KMaxPooling)

0.3.2

Change Log
Major Features and Improvements

- Add [DIEN](https://deepctr-doc.readthedocs.io/en/latest/Features.html#dien-deep-interest-evolution-network)
- Add [NFFM](https://deepctr-doc.readthedocs.io/en/latest/Features.html#nffm-field-aware-neural-factorization-machine)

Page 5 of 8

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.