jwr1995/dc1d
A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.
This project offers a specialized 1D deformable convolutional layer for deep learning models, particularly useful in time-series and sequential data processing. It takes in a 1D input sequence and a corresponding set of learned offsets, producing a transformed 1D output sequence. Researchers and practitioners in machine learning who work with sequence data, such as audio, sensor readings, or text, would use this to build more flexible neural networks.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning researcher or engineer building neural networks with PyTorch and need a 1D deformable convolutional layer for processing sequential data, without the hassle of compiling custom C++ or CUDA extensions.
Not ideal if you are looking for a pre-trained model or a complete solution for a specific domain problem, as this is a fundamental building block for deep learning architectures.
Stars
46
Forks
4
Language
Python
License
MIT
Category
Last pushed
Aug 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jwr1995/dc1d"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...