Deformable-ConvNets 
 Deformable CNNs framework
 A software framework implementing Deformable Convolutional Networks for object detection and image segmentation tasks
Deformable Convolutional Networks
160 stars
 18 watching
 27 forks
 
Language: Python 
last commit: almost 8 years ago 
Linked from   1 awesome list  
 Related projects:
| Repository | Description | Stars | 
|---|---|---|
|    |  A Python implementation of a Convolutional Neural Network from scratch using NumPy for building CNNs from scratch | 577 | 
|    |  An implementation of a lightweight convolutional neural network architecture for mobile devices | 191 | 
|    |  A deep learning framework implementation of higher-order graph convolutional architectures and their applications | 403 | 
|    |  Deep learning models for semantic segmentation of images | 101 | 
|    |  PyTorch implementation of graph ConvNets using spectral filtering | 291 | 
|    |  A library implementing a Fully Convolutional Network architecture with Keras support | 202 | 
|    |  An implementation of fully convolutional networks in Chainer, a deep learning framework. | 218 | 
|    |  Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed. | 22 | 
|    |  A TensorFlow implementation of a graph convolution algorithm using wavelet transforms instead of traditional methods. | 64 | 
|    |  An implementation of Deformable Convolution in PyTorch using CUDA. | 409 | 
|    |  Provides an implementation of convolutional neural networks in MATLAB. | 98 | 
|    |  An efficient CNN architecture for mobile devices with learned group convolutions and dense connectivity | 694 | 
|    |  A repository providing pre-trained models and results for image deconvolution in the presence of kernel/model uncertainty | 14 | 
|    |  An implementation of a deep learning algorithm for image segmentation using convolutional neural networks | 220 | 
|    |  An implementation of a fully convolutional network architecture for image segmentation using VGG weights. | 1,102 |