A. Jabri

megablocks. Python

megablocks-public.

recurrent-interface-network-pytorch. Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

dense-ulearn-vos. Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

sfseg. [IJCAI 2020] A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time

pytorch_block_sparse. Fast Block Sparse Matrices for Pytorch

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

TorchPQ. Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda

up-detr. [TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

Image-Local-Attention. A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.

vissl. VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

mrcl. Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"

visdom. A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

rigidmask. Code for "Learning to Segment Rigid Motions from Two Frames". CVPR 2021.

rlkit-relational. Codebase for ICRA 2020 paper "Towards Practical Multi-object Manipulation using Relational Reinforcement Learning"

negative-margin.few-shot. PyTorch implementation of “Negative Margin Matters: Understanding Margin in Few-shot Classification”

MemDPC. [ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

pytorch-softdtw-cuda. Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

pytorch-blender. :sweat_drops: Seamless, distributed, real-time integration of Blender into PyTorch data pipelines

TorchRay. Understanding Deep Networks via Extremal Perturbations and Smooth Masks

DPC. Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

PyTorch-NEAT. Python

noise-as-targets. Unsupervised Learning by Predicting Noise

House3D. a Realistic and Rich 3D Environment

podcast-alarm. An alarm clock that plays your favorite NPR podcast

pytorch-visdom. Support powerful visual logging in PyTorch.

pytorch-maml. PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400

vqs. VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

fastText. Library for fast text representation and classification.

bombora. My experimentations with Reinforcement Learning in Pytorch

torch-rnnlib. This library provides utilities for creating and manipulating RNNs to model sequential data.

adaptive-softmax. Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

CommAI-env. A platform for developing AI systems as described in A Roadmap towards Machine Intelligence - http://arxiv.org/abs/1511.08130

ajabri.github.io. JavaScript

blur-detection. Some implementations of algorithms for blur detection in JPEGs

bundler_sfm. Bundler Structure from Motion Toolkit