Amir Rosenfeld's repositories
incremental_learning
Initial Code for the paper "incremental learning through deep adaptation"
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
pytorch-classification
Classification with PyTorch.
CaffeFeaturesExample
Sample code for classifying images into two categories using Caffe features + SVM.
character-based-cnn
Implementation of character based convolutional neural network
Compositional-Attention-Networks-for-Machine-Reasoning-PyTorch
A PyTorch implementation of Compositional Attention Networks
detectron2
Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
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.
faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn
LegoBrickClassification
Repository to identify Lego bricks automatically only using images
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
pytorch-rl
Deep Reinforcement Learning with pytorch & visdom
pytorch-semantic-segmentation
PyTorch for Semantic Segmentation
pytorch-yolo2
Convert https://pjreddie.com/darknet/yolo/ into pytorch
relational-networks
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)
rosenfeldamir.github.io
Personal Website
semantic-segmentation-pytorch
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
simple_dqn
Simple deep Q-learning agent.
ssd.pytorch-p
A PyTorch Implementation of Single Shot MultiBox Detector
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)
torchvideo
:movie_camera: Datasets, transforms and samplers for video in PyTorch
vision_utils
lightweight utilities for computer-vision projects and other miscellanea