CoordConv-pytorch

Coordinate transformer

An implementation of a convolutional neural network component that handles spatial coordinates.

Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (https://arxiv.org/pdf/1807.03247.pdf)

GitHub

397 stars
18 watching
50 forks
Language: Python
last commit: about 8 years ago

Related projects:

RepositoryDescriptionStars
kimhc6028/relational-networksA PyTorch implementation of a neural network module for relational reasoning in computer vision tasks809
jhcho99/coformerAn implementation of a deep learning model for grounding situation recognition in images45
eladhoffer/convnet.pytorchA PyTorch implementation of various deep convolutional networks for efficient training and evaluation on diverse datasets.347
koz4k/dni-pytorchDecoupled Neural Interfaces using Synthetic Gradients for PyTorch236
kaiyangzhou/dassl.pytorchA PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision.1,236
pyproj4/pyprojA Python interface to PROJ, enabling coordinate transformations and projections in geospatial applications.1,074
xiadingz/video-caption.pytorchPyTorch implementation of video captioning, combining deep learning and computer vision techniques.402
pochih/fcn-pytorchA Python implementation of fully convolutional networks for semantic segmentation in computer vision.409
prabhuomkar/pytorch-cppA C++ implementation of PyTorch tutorials1,978
andrewliao11/dni.pytorchAn implementation of synthetic gradients to decouple neural network layers and enable scalable communication between them119
nexusapoorvacus/deepvariationstructuredrlAn implementation of reinforcement learning for visual relationship and attribute detection using PyTorch.63
zhanghang1989/pytorch-encodingA Python framework for building deep learning models with optimized encoding layers and batch normalization.2,044
kazuto1011/deeplab-pytorchPyTorch implementation of DeepLab v2 for semantic segmentation on COCO-Stuff and PASCAL VOC datasets1,098
robotlocomotion/pytorch-dense-correspondenceThis project presents a method for learning dense object descriptors from self-supervised data, enabling tasks such as robotic manipulation and object recognition.561
benedekrozemberczki/capsgnnA PyTorch implementation of a graph neural network architecture1,246