or-toledano

AdaIN-style

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

animation-with-keypoint-mask

Deep motion transfer

autoencoder

Autoencoder + hypertuning module in PyTorch

CLIP

Contrastive Language-Image Pretraining

CodeT5

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

reinforcement-learning-dqn

DQN for Atari games (tested on Pong, Breakout)

sudoku-gurobi

Dynamically allocated M by N sudoko board, game logic and LP/ILP solver (university project)

tensor-coin

Blockchain, polymorphic (runtime CPU/GPU(CUDA) dynamic type) custom hash, and validator, built from scratch.

university-operating-systems

kmodule, pthreads, signals, ...

visual-data-extractor

Computer Vision utilities for visual data extraction

or-toledano/animation-with-keypoint-mask

Deep motion transfer

or-toledano/AdaIN-style

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

or-toledano/autoencoder

Autoencoder + hypertuning module in PyTorch

or-toledano/CLIP

Contrastive Language-Image Pretraining

or-toledano/CodeT5

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

or-toledano/reinforcement-learning-dqn

DQN for Atari games (tested on Pong, Breakout)

or-toledano/sudoku-gurobi

Dynamically allocated M by N sudoko board, game logic and LP/ILP solver (university project)

or-toledano/tensor-coin

Blockchain, polymorphic (runtime CPU/GPU(CUDA) dynamic type) custom hash, and validator, built from scratch.

or-toledano/university-operating-systems

kmodule, pthreads, signals, ...

or-toledano/visual-data-extractor

Computer Vision utilities for visual data extraction

or-toledano/cs231n.github.io

Public facing notes page

or-toledano/draw-YOLO-box

Draw bounding boxes on raw images based on YOLO format annotation. Help to check the correctness of annotation and extract the images with wrong boxes.

or-toledano/first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

or-toledano/graph-mclcl

or-toledano/learnopencv

Learn OpenCV : C++ and Python Examples

or-toledano/opencv

Open Source Computer Vision Library

or-toledano/Oscar

Oscar and VinVL

or-toledano/retinaface-tf2

RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.

or-toledano/vissl

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

or-toledano/VNext

Next-generation Video instance recognition framework on top of Detectron2 which supports SeqFormer(ECCV Oral) and IDOL(ECCV Oral))

or-toledano/yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite