Amir Rosenfeld's repositories
torchvideo
:movie_camera: Datasets, transforms and samplers for video in PyTorch
fastdup
FastDup is a tool for gaining insights from a large image collection. It can find anomalies, duplicate and near duplicate images, clusters of similaritity, learn the normal behavior and temporal interactions between images. It can be used for smart subsampling of a higher quality dataset, outlier removal, novelty detection of new information to be sent for tagging. FastDup scales to millions of images running on CPU only.
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
iv
minimalist opencv-based image viewer/browser
LegoBrickClassification
Repository to identify Lego bricks automatically only using images
detectron2
Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
vision_utils
lightweight utilities for computer-vision projects and other miscellanea
incremental_learning
Initial Code for the paper "incremental learning through deep adaptation"
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
character-based-cnn
Implementation of character based convolutional neural network
strike-with-a-pose
A simple GUI tool for generating adversarial poses of objects.
texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019)
TotallyLooksLike
Accompanying code for the paper: Totally Looks Like - How Humans Compare, Compared to Machines, by Amir Rosenfeld, Markus D. Solbach and John K. Tsotsos
faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn
pytorch-classification
Classification with PyTorch.
rosenfeldamir.github.io
Personal Website
sunets
PyTorch Implementation of Stacked U-Nets (SUNets)
Compositional-Attention-Networks-for-Machine-Reasoning-PyTorch
A PyTorch implementation of Compositional Attention Networks
pytorch-rl
Deep Reinforcement Learning with pytorch & visdom
relational-networks
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)
semantic-segmentation-pytorch
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
Arnold
Arnold - DOOM Agent
pytorch-semantic-segmentation
PyTorch for Semantic Segmentation
pytorch-yolo2
Convert https://pjreddie.com/darknet/yolo/ into pytorch
ssd.pytorch-p
A PyTorch Implementation of Single Shot MultiBox Detector
simple_dqn
Simple deep Q-learning agent.
CaffeFeaturesExample
Sample code for classifying images into two categories using Caffe features + SVM.