deformable-convolution-pytorch
by 1zb
PyTorch implementation of Deformable Convolution
AI summary
Deformable Convolver
An implementation of Deformable Convolution in PyTorch using CUDA.
- stars
- 409
- forks
- 53
- watching
- 18
Similar projects
Found by comparing what the projects do, not just their names.
ConvNet library
A PyTorch implementation of various deep convolutional networks for efficient training and evaluation on diverse datasets.
Deformable CNNs framework
A software framework implementing Deformable Convolutional Networks for object detection and image segmentation tasks
Image Blender
A PyTorch implementation of blending images by optimizing a Poisson loss with style and content loss
Deep learning library
Provides a CUDA backend for the PyTorch deep learning framework
FFT transformer
Provides an efficient wrapper around CUDA FFTs for PyTorch transformations
Convolutional regularizer
Regularizes convolutional networks by randomly dropping units in contiguous regions of feature maps
Coordinate transformer
An implementation of a convolutional neural network component that handles spatial coordinates.
Segmentation library
A PyTorch implementation of FCN for semantic segmentation with an easy-to-use interface and pre-trained models.
Message passing abstraction
Decoupled Neural Interfaces using Synthetic Gradients for PyTorch
Decoupled Neural Interface
An implementation of synthetic gradients to decouple neural network layers and enable scalable communication between them
Adversarial attacks library
PyTorch implementation of various Convolutional Neural Network adversarial attack techniques
Model fine-tuner
Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch.
Image deblurring software
Implementation of an algorithm for single image deblurring in images with defocus blur
Deep learning model
An implementation of a deep learning model using PyTorch and depthwise separable convolutions for image classification
Video captioner
PyTorch implementation of video captioning, combining deep learning and computer vision techniques.
