jhjin / Flattened Cnn
Licence: mit
Flattened convolutional neural networks (1D convolution modules for Torch nn)
Stars: ✭ 59
Labels
Projects that are alternatives of or similar to Flattened Cnn
Pamtri
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification (ICCV 2019) - Official PyTorch Implementation
Stars: ✭ 53 (-10.17%)
Mutual labels: cuda
Cuda Samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Stars: ✭ 1,087 (+1742.37%)
Mutual labels: cuda
Hungariangpu
An GPU/CUDA implementation of the Hungarian algorithm
Stars: ✭ 51 (-13.56%)
Mutual labels: cuda
3d Ken Burns
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
Stars: ✭ 1,073 (+1718.64%)
Mutual labels: cuda
Qualia2.0
Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.
Stars: ✭ 41 (-30.51%)
Mutual labels: cuda
Dokai
Collection of Docker images for ML/DL and video processing projects
Stars: ✭ 58 (-1.69%)
Mutual labels: cuda
Carlsim3
CARLsim is an efficient, easy-to-use, GPU-accelerated software framework for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.
Stars: ✭ 52 (-11.86%)
Mutual labels: cuda
Nvbio Gpl
NVBIO is a library of reusable components designed to accelerate bioinformatics applications using CUDA.
Stars: ✭ 56 (-5.08%)
Mutual labels: cuda
Singularity Tutorial
Tutorial for using Singularity containers
Stars: ✭ 46 (-22.03%)
Mutual labels: cuda
Cuda Convnet2.torch
Torch7 bindings for cuda-convnet2 kernels!
Stars: ✭ 42 (-28.81%)
Mutual labels: cuda
Deformable conv2d pytorch
deformable_conv2d layer implemented in pytorch
Stars: ✭ 53 (-10.17%)
Mutual labels: cuda
Hzproc
torch data augmentation toolbox (supports affine transform)
Stars: ✭ 56 (-5.08%)
Mutual labels: cuda
Flattened convolutional neural networks
This package has 1D convolution modules (over channel, in vertical, in horizontal) used in [Flattened Convolutional Neural Networks for Feedforward Acceleration] (http://arxiv.org/abs/1412.5474) where we denote the flattened convolution layer as a sequence of one-dimensional filters across all 3D directions.
Install
Choose both or either of nn/cunn backend packages depending on your computing environment.
luarocks install https://raw.githubusercontent.com/jhjin/flattened-cnn/master/nnconv1d-scm-1.rockspec # cpu
luarocks install https://raw.githubusercontent.com/jhjin/flattened-cnn/master/cunnconv1d-scm-1.rockspec # cuda
or use this command if you already cloned this repo.
cd nn-conv1d
luarocks make rocks/nnconv1d-scm-1.rockspec
cd ../cunn-conv1d
luarocks make rocks/cunnconv1d-scm-1.rockspec
Available modules
This is a list of available modules.
nn.LateralConvolution(nInputPlane, nOutputPlane) -- 1d conv over feature
nn.HorizontalConvolution(nInputPlane, nOutputPlane, kL) -- 1d conv in horizontal
nn.VerticalConvolution(nInputPlane, nOutputPlane, kL) -- 1d conv in vertical
Example
Run the command below.
th example.lua
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].