A python toolbox for Trajectory Deep Learning.
Project description
A python toolkit for Trajectory Deep Learning.
TrajDL提供了轨迹数据挖掘领域中的多个SOTA深度学习模型的实现,为研究人员、工程师提供易用、高效、可靠的开发工具,可以快速开展实验和应用开发。TrajDL有几个关键特性:
-
基于Arrow,Pytorch和Lightning
TrajDL的数据部分构建在Arrow之上,模型部分构建在Pytorch之上,训练与验证流程构建在Lightning之上,充分结合各个框架工具的优势。 -
高效的工具
TrajDL提供了高效的工具,比如高效的Dataset,Tokenizer,GridSystem。出色的零拷贝特性可以显著降低数据的处理时间,节省内存使用。高效的Tokenizer和GridSystem可以随时转换数据,无需预先处理数据。 -
可扩展性
TrajDL高度模块化,不会约束用户的代码,用户可以随时从TrajDL里面取出自己需要使用的工具。TrajDL还打通了与Polars,Pandas,PyArrow等工具的接口,用户使用常用的科学计算工具处理后的数据可以轻松导入到TrajDL的数据体系。另外TrajDL同时支持API与配置文件两种方式开展实验与开发,尽可能提升用户体验。 -
包含SOTA模型的实验复现脚本
TrajDL提供了SOTA模型的复现脚本,用户可以通过脚本重现论文内的实验结果,部分场景下TrajDL具备比论文场景更优的效果。
文档 📕
简体中文文档参阅:简体中文文档
English documentation will be provided in subsequent versions.
Benchmark 🚀
scripts/benchmark目录下存储了TrajDL提供的benchmark复现脚本,针对各个论文使用TrajDL进行了实验复现。
License
本项目使用Apache License 2.0,详见LICENSE。
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file trajdl-0.1.0.dev1.tar.gz.
File metadata
- Download URL: trajdl-0.1.0.dev1.tar.gz
- Upload date:
- Size: 961.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b916d0f28d3f849963bcc7034a849af9b50d1a258bae8bd686c60ae55c16ee00
|
|
| MD5 |
2af39b44e0cd65aa3084756808e42ecd
|
|
| BLAKE2b-256 |
698dfebd133d107dc62ec99bc8402f516b6779bcf5a083e578768b0929e1bac3
|
File details
Details for the file trajdl-0.1.0.dev1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: trajdl-0.1.0.dev1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 265.1 kB
- Tags: CPython 3.12, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
92e7944150d83a6bb1749f25a2d0d0962d3c8beb1fa38c1493e1f1f98c03031a
|
|
| MD5 |
b906101b9e62e41915cc757ee2fdbde8
|
|
| BLAKE2b-256 |
6b0b10b9cd1816289c236b098285fbe4f2e1310d62bf726feafbecf05c208a18
|
File details
Details for the file trajdl-0.1.0.dev1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: trajdl-0.1.0.dev1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 265.2 kB
- Tags: CPython 3.11, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
01ba7c36d7b0a6c3dde67c70ebd8442bc82b61bb44e7480d0528c5397ff165ee
|
|
| MD5 |
a7da9c9f707de0838b1017a9bc37808f
|
|
| BLAKE2b-256 |
bdf03bf061c15a24711e8f1f0e3adcac0f1b3d4264f1eb69b21d076ec73ddb05
|
File details
Details for the file trajdl-0.1.0.dev1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: trajdl-0.1.0.dev1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 264.3 kB
- Tags: CPython 3.10, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2f7c2ca557282fdf827ee358ea674de0bf42db35f1c9020c4bc1aaeb9c5449c1
|
|
| MD5 |
0ddedd319c3c253c2bd6e31aa5e815d1
|
|
| BLAKE2b-256 |
2aec7b27d2e9b631f8d5f3143ac97b650b1048727ad247c3b689721fdd309873
|