:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

A language-agnostic interface to TensorBoard

ATen: A TENsor library for C++11

2.86% and 15.85% on CIFAR-10 and CIFAR-100

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

A Compositional Object-Based Approach to Learning Physical Dynamics

Training code for the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

Real time face alignment

Torch Implementation of NIPS'16 paper: Perspective Transformer Nets

Torch implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).

3D ResNets for Action Recognition

This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper.

Suravi is a small distribution of Ravi/Lua 5.3 with batteries such as cjson, lpeglabel, luasocket, penlight, torch7, luv, luaossl

No description provided.

Implementation of "Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network" by Z.Laskar et al.

Code for the paper entitled "Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods".

Torch implementation for MDNet: A Semantically and Visually Interpretable Medical Image Diagnosis Network

A collection of popular datasets for deep learning.

Video classification tools using 3D ResNet

Autoencoder trained on ImageNet Using Torch 7

An unofficial Torch implementation of InfoGAN

Temporal augmentation with two-stream ConvNet features on human action recognition

Deep reinforcement learning package for torch7

Human activity recognition using human pose information to aid classification.

No description provided.

SSD : Single Shot MultiBox Detector for torch7

Non Negative Sparse AutoEncoder (NNSAE). An efficient online learning scheme for non-negative and sparse coding in autoencoder neural networks.

Demo code for "Change Detection by Training a Triplet Netowk for Motion Feature Extraction"