rec4torch
推荐系统的pytorch算法实现
1. 下载安装
安装稳定版
pip install rec4torch
安装最新版
pip install git+https://www.github.com/Tongjilibo/rec4torch.git
2. 功能
- 核心功能:基于pytorch实现各类推荐算法(DeepFM, WideDeep, DCN, DIN, DIEN)
- 主要区别:相对于deep-ctr, 去除对tensorflow和keras的依赖,去除重复过embedding的操作,原生支持multiclass
- 训练过程:
2022-10-28 23:16:10 - Start Training 2022-10-28 23:16:10 - Epoch: 1/5 5000/5000 [==============================] - 13s 3ms/step - loss: 0.1351 - acc: 0.9601 Evaluate: 100%|██████████████████████████████████████████████████| 2500/2500 [00:03<00:00, 798.09it/s] test_acc: 0.98045. best_test_acc: 0.98045 2022-10-28 23:16:27 - Epoch: 2/5 5000/5000 [==============================] - 13s 3ms/step - loss: 0.0465 - acc: 0.9862 Evaluate: 100%|██████████████████████████████████████████████████| 2500/2500 [00:03<00:00, 635.78it/s] test_acc: 0.98280. best_test_acc: 0.98280 2022-10-28 23:16:44 - Epoch: 3/5 5000/5000 [==============================] - 15s 3ms/step - loss: 0.0284 - acc: 0.9915 Evaluate: 100%|██████████████████████████████████████████████████| 2500/2500 [00:03<00:00, 673.60it/s] test_acc: 0.98365. best_test_acc: 0.98365 2022-10-28 23:17:03 - Epoch: 4/5 5000/5000 [==============================] - 15s 3ms/step - loss: 0.0179 - acc: 0.9948 Evaluate: 100%|██████████████████████████████████████████████████| 2500/2500 [00:03<00:00, 692.34it/s] test_acc: 0.98265. best_test_acc: 0.98365 2022-10-28 23:17:21 - Epoch: 5/5 5000/5000 [==============================] - 14s 3ms/step - loss: 0.0129 - acc: 0.9958 Evaluate: 100%|██████████████████████████████████████████████████| 2500/2500 [00:03<00:00, 701.77it/s] test_acc: 0.98585. best_test_acc: 0.98585 2022-10-28 23:17:37 - Finish Training
3. 快速上手
- 参考了deepctr-torch, 使用torch4keras中作为Trainer
- 测试用例
4. 版本说明
- v0.0.2:20240204 更新依赖项torch4keras版本
- v0.0.1:20221027 dcn, deepcrossing, deepfm, din, dien, wide&deep, ncf等模型,训练过程修改为传入dataloader,合并models和layers,合并简化embedding_lookup,去掉一些重复的embedding过程(提速)
5. 更新:
- 20240204:更新依赖项torch4keras版本
- 20221110:增加自定义的TensorDataset和collate_fn_device,支持指定device,防止显存占用多大,用out_dim和loss来替代task参数,兼容多分类
- 20221027:增加deepcrossing, ncf, din, dien算法,使用torch4keras作为trainer
- 20220930:初版提交, 训练过程修改为传入dataloader(参考bert4torch),合并models和layers(模型结构较简单),合并简化embedding_lookup,去掉一些重复的embedding过程(提速)
Metadata
Release files for rec4torch 0.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| rec4torch-0.0.2.tar.gz | 20.3 kB | Without provenance | Details for rec4torch-0.0.2.tar.gz |
Release files / rec4torch-0.0.2.tar.gz
| Download URL | rec4torch-0.0.2.tar.gz |
|---|---|
| Size | 20.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b2efe865cb794d573847a6be11955f547c84f1eaa1a0ab918c4774304fd81643
|
|
BLAKE2b-256 checksum How to use checksums |
4b97bfe5f667115c4c1822906cca7944c71423d70c75aecd7274bf1037651fba
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.30.0 requests-toolbelt/0.9.1 urllib3/1.26.4 tqdm/4.64.1 importlib-metadata/4.8.2 keyring/22.3.0 rfc3986/1.5.0 colorama/0.4.4 CPython/3.8.8
|
Security for rec4torch 0.0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.