bogger's repositories
caffe-multigpu
Originally cloned from puzzledqs's mpi-parallel version. This version uses MPI to enable multi-GPU processing. Also includes some useful scripts for the paper "A Large-Scale Car Dataset for Fine-Grained Categorization and Verification", CVPR 2015. Check "models/finetune_web_car" for details.
caffe-multilabel
Note: This is already a very old caffe version. Please check the caffe-multigpu repo for a new version based on caffe-rc (https://github.com/BVLC/caffe/releases/tag/rc). Multilabel caffe, with multiple label outputs on dataLayer. No need to modify Loss layer, each loss is dealed separately.
arctic-capgen-vid
automatic video description generation with GPU training
C3D
C3D is a modified version of BVLC caffe to support 3D ConvNets.
caffe
A fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please see the original readme.
char-rnn
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Crepe
Character-level Convolutional Networks for Text Classification
densecap
Dense image captioning in Torch
gfx.js
A graphics backend for the browser (with a Torch7 client).
neuraltalk2
Efficient Image Captioning code in Torch, runs on GPU
rubygems
Library packaging and distribution for Ruby.
skip-thoughts
Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"
zhihu-oauth
尝试解析出知乎官方未开放的 OAuth2 接口,并提供优雅的使用方式,作为 zhihu-py3 项目的替代者,目前还在实验阶段