DeepMatch Files

A deep matching model library for recommendations & advertising

This is an exact mirror of the DeepMatch project, hosted at https://github.com/shenweichen/DeepMatch. SourceForge is not affiliated with DeepMatch.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
deepmatch-0.3.0.tar.gz	2022-07-03	19.3 kB	0
deepmatch-0.3.0-py3-none-any.whl	2022-07-03	29.1 kB	0
README.md	2022-07-03	1.9 kB	0
v0.3.0 source code.tar.gz	2022-07-03	973.9 kB	0
v0.3.0 source code.zip	2022-07-03	1.0 MB	0
Totals: 5 Items		2.0 MB	0

DeepMatch

⚠️This version does not support backward compatibility

this verson is not compatible with v0.2. and v0.1.
该版本不支持向下兼容，请按照样例进行完整的样本处理和模型构建

Major Features and Improvements

Support different negative sampling strategies, including inbatch, uniform, frequency, adaptive. @shenweichen
refactor & update preprocess.py, @shenweichen
DSSM inbatch negative sampling example
YoutubeDNN/MIND frequency negtivte sampling example
SDM frequency negtivte sampling example

API Changes

Add new class deepmatch.utils.NegativeSampler
Remove deepmatch.layers.core.Similarity
Add sampler_config,loss_type parameters for models
Change gamma to temperature,gamma=1/temperature

DisscussionGroup

Github Discussions
Wechat Discussions

公众号：浅梦学习笔记	微信：deepctrbot	学习小组加入主题集合

Source: README.md, updated 2022-07-03

Other Useful Business Software

$300 Free Credits to Build on Google Cloud Icon

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Build Securely on AWS with Proven Frameworks Icon

Build Securely on AWS with Proven Frameworks

Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.

Download Now

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Recommended Projects

VectorChord
Scalable, fast, and disk-friendly vector search in Postgres
StarSpace
Learning embeddings for classification, retrieval and ranking
TRELLIS.2
Native and Compact Structured Latents for 3D Generation
Image classification models for Keras
Keras code and weights files for popular deep learning models
Keras.js
Run Keras models in the browser, with GPU support using WebGL