MONAI Label MONAI Label is a server-client system that facilitates interactive medical image annotation by using AI. It is an open-source and easy-to-install ecosystem that can run locally on a machine with one or two GPUs. Both server and client work on the same/different machine. However, initial support for multiple users is restricted. It shares the same principles with MONAI. Features The codebase is currently under active development. framework for developing and deploying MONAI Label Apps to train and infer […]

RetinaFace RetinaFace is a deep learning based cutting-edge facial detector for Python coming with facial landmarks. RetinaFace is the face detection module of insightface project. The original implementation is mainly based on mxnet. Then, its tensorflow based re-implementation is published by Stanislas Bertrand. This repo is heavily inspired from the study of Stanislas Bertrand. Its source code is simplified and it is transformed to pip compatible but the main structure of the reference model and its pre-trained weights are same. […]

smart-cities-drl Urban mobility simulations with Python3, RLlib (Deep Reinforcement Learning) and Mesa (Agent-based modeling) Documentation RLlib: https://docs.ray.io/en/master/rllib.html Mesa: https://mesa.readthedocs.io/en/stable/ Installation Clone repository and install dependencies. git clone [email protected]:eescriba/smart-cities-drl.git cd smart-cities-drl python3 -m venv venv source env/bin/activate pip install -r requirements.txt Training Train environments in Jupyter notebooks with RLlib. WasteNet SmartCab Simulations Run and visualize environments with Mesa. mesa runserver src/[env_name] GitHub https://github.com/eescriba/smart-cities-drl    

raw2raw Project page for the paper Semi-Supervised Raw-to-Raw Mapping 2021. Mahmoud Afifi and Abdullah Abuolaim York University Project page of the paper Semi-Supervised Raw-to-Raw Mapping. Mahmoud Afifi and Abdullah Abuolaim. arXiv preprint arXiv:2106.13883, 2021. If you use this code, please cite our paper: @article{afifi2021raw2raw, title={Semi-Supervised Raw-to-Raw Mapping}, author={Afifi, Mahmoud and Abuolaim, Abdullah}, journal={arXiv preprint arXiv:2106.13883}, year={2021} } Abstract The raw-RGB colors of a camera sensor vary due to the spectral sensitivity differences across different sensor makes and models. This paper […]

Bird-Song-Classification The goal is to classify different birds species based on their songs/calls. Spectrograms have been extracted from the audio samples and used as features for classification. A Siamese network based on 1D dilated convolutions is used here. Model is trained using triplet loss. I am using the British Birdsong Dataset available on Kaggle for this experiment. Download the data from here. This dataset is a subset of Xeno-Canto database. Siamese Networks along with dilated 1D convolutions are used here […]

Spectral Tensor Train Parameterization of Deep Learning Layers This repository is the official implementation of our AISTATS 2021 paper titled “Spectral Tensor Train Parameterization of Deep Learning Layers” by Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, and Luc Van Gool [arXiv] [PMLR]. It demonstrates how to perform low-rank neural network reparameterization and its stable training in a compressed form. The code provides all experiments (GAN and Image Classification) from the paper (see configs/aistats21 directory) with […]

ElegantRL ElegantRL is featured with lightweight, efficient and stable, for researchers and practitioners. Lightweight: The core codes <1,000 lines (check elegantrl/tutorial), using PyTorch (train), OpenAI Gym (env), NumPy, Matplotlib (plot). Efficient: performance is comparable with Ray RLlib. Stable: as stable as Stable Baseline 3. Currently, model-free deep reinforcement learning (DRL) algorithms: DDPG, TD3, SAC, A2C, PPO, PPO(GAE) for continuous actions DQN, DoubleDQN, D3QN for discrete actions For DRL algorithms, please check out the educational webpage OpenAI Spinning Up. File Structure […]

CLCC CLCC: Contrastive Learning for Color Constancy (CVPR 2021)Yi-Chen Lo*, Chia-Che Chang*, Hsuan-Chao Chiu, Yu-Hao Huang, Chia-Ping Chen, Yu-Lin Chang, Kevin Jou MediaTek Inc., Hsinchu, Taiwan (*) indicates equal contribution. We preprocess each fold of dataset and stored in .pkl format for each sample. Each sample contains: Raw image: Mask color checker; Subtract black level; Convert to uint16 [0, 65535] BGR numpy array with shape (H, W, 3). RGB label: L2-normalized numpy vector with shape (3,). Color checker: [0, 4095] […]

Graph Transformer – Pytorch Implementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2. This was recently used by both Costa et al and Bakers lab for transforming MSA and pair-wise embedding into 3d coordinates. Todo add rotary embeddings for injecting adjacency information Install $ pip install graph-transformer-pytorch Usage import torch from graph_transformer_pytorch import GraphTransformer model = GraphTransformer( dim = 256, depth = 6, edge_dim = 512, # optional – if left out, edge dimensions is assumed to […]