Welcome to DeepCTR-Torch’s documentation!

DeepCTR-Torch is a Easy-to-use , Modular and Extendible package of deep-learning based CTR models along with lots of core components layer which can be used to build your own custom model easily.It is compatible with PyTorch.You can use any complex model with model.fit() and model.predict().

Let’s Get Started! (Chinese Introduction)

You can read the latest code at https://github.com/shenweichen/DeepCTR-Torch and DeepCTR for tensorflow version.

News

04/18/2026 : Release v0.3.0 with improved compatibility for Python 3.7 ~ 3.13 and PyTorch 2.4+. CI now includes examples smoke tests. Changelog

10/22/2022 : Add multi-task models: SharedBottom, ESMM, MMOE, PLE. Changelog

06/19/2022 : Fix some bugs. Changelog

06/14/2021 : Add AFN and fix some bugs. Changelog

DisscussionGroup

公众号：浅梦学习笔记 wechat ID: deepctrbot

Discussions 学习小组主题集合

Home:

• Quick-Start
  • Installation Guide
  • Getting started: 4 steps to DeepCTR-Torch
• Features
  • Overview
  • Feature Columns
  • Models
  • MultiTask Models
  • Layers
• Examples
  • Classification: Criteo
  • Regression: Movielens
  • Multi-value Input : Movielens
  • MultiTask Learning:MMOE
• FAQ
  • 1. Save or load weights/models
  • 2. Set learning rate and use earlystopping
  • 3. How to add a long dense feature vector as a input to the model?
  • 4. How to run the demo with GPU ?
  • 5. How to run the demo with multiple GPUs ?
• History

API:

• Models
  • BaseModel
  • CCPM
  • PNN
  • WDL
  • DeepFM
  • MLR
  • NFM
  • AFM
  • DCN
  • DCN-Mix
  • DIN
  • DIEN
  • xDeepFM
  • AutoInt
  • ONN
  • FiBiNET
  • IFM
  • DIFM
  • SharedBottom
  • ESMM
  • MMOE
  • PLE
• Layers
  • Core Layers
  • Interaction Layers
  • Sequence Layers
• Callbacks

Indices and tables

• Index

• Module Index

• Search Page