Simple demonstration of separable convolutions
翻译 - 可分离卷积的简单演示
A PyTorch implementation of Xception: Deep Learning with Depthwise Separable Convolutions
Spatiotemporal-separable 3D convolution network.
Reference implementation for Blueprint Separable Convolutions (CVPR 2020)
An implementation of Adaptive Separable Convolution for Video Frame Interpolation
Simple Speech Keyword Detecting with Depthwise Separable Convolutions | DLology
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
deeplabv3plus2018:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Implementation of Depthwise Separable Convolution (pytorch)
Convolutions for Sequence Modeling
Separable Subsurface Scattering is a technique that allows to efficiently perform subsurface scattering calculations in screen space in just two passes.
Cheng-Hao Tu, Jia-Hong Lee, Yi-Ming Chan and Chu-Song Chen, "Pruning Depthwise Separable Convolutions for MobileNet Compression," International Joint Conference on Neural Networks, IJCNN 2020, July 20...
PyTorch code for the "Deep Neural Networks with Box Convolutions" paper
翻译 - 用于“具有盒卷积的深度神经网络”的PyTorch代码
Representation learning on large graphs using stochastic graph convolutions.
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
Convmelspec: Convertible Melspectrograms via 1D Convolutions
Implementation of YOLOv3-tiny + Depthwise Separable Convolution on FPGA
Experiments with Group Equivariant Convolutions in PyTorch
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"