AI Rank
中文
← Open Source
oeway

pytorch-deform-conv

PyTorch implementation of Deformable Convolution.

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
904
Stars
146
Forks
+0
This week
1
Contributors
Created 2017-04-04 · Updated 2026-07-30 · #12761 today
Top developers
oeway

oeway/pytorch-deform-conv is ranked 12,761 with 904 stars.

Same-category comparison

oeway/pytorch-deform-conv is ranked 12,761 among these 8 peers; autonomousvision/projected-gan is ranked 12,758.

Same-category comparison
NameRankMetrics
songgc/TF-recomm12,752
Language:
Python
Stars:
905
Forks:
215
Description:
Tensorflow-based Recommendation systems.
Lux-AI-Challenge/Lux-Design-S112,755
Language:
Jupyter Notebook
Stars:
904
Forks:
145
Description:
Home to the design and engine of the @Lux-AI-Challenge Season 1, hosted on @kaggle.
Natooz/MidiTok12,756
Language:
Python
Stars:
904
Forks:
106
Description:
MIDI / symbolic music tokenizers for Deep Learning models 🎶.
autonomousvision/projected-gan12,758
Language:
Python
Stars:
904
Forks:
99
Description:
[NeurIPS'21] Projected GANs Converge Faster.
williamSYSU/TextGAN-PyTorch12,765
Language:
Python
Stars:
904
Forks:
202
Description:
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
IDEA-Research/Motion-X12,766
Language:
Python
Stars:
903
Forks:
25
Description:
[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset".
Kautenja/gym-super-mario-bros12,768
Language:
Python
Stars:
903
Forks:
173
Description:
Gymnasium environments for NES Mario games, with task metadata, reward instrumentation, and reproducible evaluation interfaces.
MathiasGruber/PConv-Keras12,769
Language:
Jupyter Notebook
Stars:
903
Forks:
246
Description:
Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
Stars904
Forks146
Contributors1
Created date2017-04-04
Updated date2026-07-30
Stars in 1 day0
Stars in 7 days0
Rank12,761
Previous rank12,663
Rank change-98
7-day stars rank13,592
Previous 7-day stars rank13,605
7-day stars rank change13
Total stars rank12,044
Previous total stars rank12,021
Total stars rank change-23
CountrySweden
README summary

PyTorch implementation of Deformable Convolution **! Warning: There is some issues in this implementation and this repo is not maintained any more, please consider using for example: TORCHVISION. The following animation is generated by Felix Lau (with his tensorflow implementation): Also Check out Felix Lau's summary of the paper:

Frequently asked questions

How many stars and forks are recorded?

oeway/pytorch-deform-conv has 904 stars and 146 forks.

What is the repository rank?

oeway/pytorch-deform-conv is ranked 12,761.

What language and category are recorded?

oeway/pytorch-deform-conv has 904 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

oeway/pytorch-deform-conv is compared with autonomousvision/projected-gan, ranked 12,758 with 904 stars.

README

PyTorch implementation of Deformable Convolution

!!!Warning: There is some issues in this implementation and this repo is not maintained any more, please consider using for example: TORCHVISION.OPS.DEFORM_CONV

TODO List

  • [x] implement offsets mapping in pytorch
  • [x] all tests passed
  • [x] deformable convolution module
  • [x] Fine-tuning the deformable convolution modules
  • [x] scaled mnist demo
  • [x] improve speed with cached grid array
  • [ ] use MNIST dataset from pytorch (instead of Keras)
  • [ ] support input image with different width and height
  • [ ] benchmark with tensorflow implementation

Deformable Convolutional Networks

Dai, Jifeng, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei. 2017. “Deformable Convolutional Networks.” arXiv [cs.CV]. arXiv. http://arxiv.org/abs/1703.06211

The following animation is generated by Felix Lau (with his tensorflow implementation):

Also Check out Felix Lau's summary of the paper: https://medium.com/@phelixlau/notes-on-deformable-convolutional-networks-baaabbc11cf3

Nearby in the ranking
Similar items