brian6091

CombiningExchangeablePValues. Combining exchangeable p-values

Reaction-Lights-Training-Module. Reactive Light Training Module used in fitness for developing agility and reaction speed.

multitaper_toolbox. A multitaper spectral estimation toolbox implemented in MATLAB, Python, and R

autoMaqFACS. Matlab code for autoMaqFACS classification

openface. Face recognition with deep neural networks.

Atlas. Atlas: End-to-End 3D Scene Reconstruction from Posed Images

STIT. Python

MultiDiffusion. Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

archai. Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.

nni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

lion-pytorch. 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

ssast. Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

ast. Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

DeepSpectrum. Python

FaceImageQuality. Code and information for face image quality assessment with SER-FIQ

Universal-Guided-Diffusion. Jupyter Notebook

GazeNet. Multi-pose video-based eye tracking

MI-BCI-by-implementing-a-frequency-band-selection. Motor Imagery-based Brain-Computer Interfaces (MI-BCI) are a promise to revolutionize the way humans interact with machinery or software, performing actions by just thinking about them. Patients suffering from critical movement disabilities, such as amyotrophic lateral sclerosis (ALS) or tetraplegia, could use this technology to control a wheelchair, robotic prostheses, or any other device that could let them interact independently with their surroundings. The focus of this project is to aid communities affected by these disorders with the development of a method that is capable of detecting, as accurately as possible, the intention to execute movements (without them occurring) in the upper extremities of the body. This will be done through signals acquired with an electroencephalogram (EEG), their conditioning and processing, and their subsequent classification with artificial intelligence models. In addition, a digital signal filter will be designed to keep the most characteristic frequency bands of each individual and increase accuracy significantly. After extracting discriminative statistical, frequential, and spatial features, it was possible to obtain an 88% accuracy on validation data when it came to detecting whether a participant was imagining a left-hand or a right-hand movement. Furthermore, a Convolutional Neural Network (CNN) was used to distinguish if the participant was imagining a movement or not, which achieved a 78% accuracy and a 90% precision. These results will be verified by implementing a real-time simulation with the usage of a robotic arm.

SpecAugment. A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

DTL_TFC_Vibration_Identification. Deep Transfer Learning and Time-Frequency Characteristics-Based Identification Method for Structural Seismic Response

Getting-Things-Done-with-Pytorch. Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BER

deeptime. Set of deep learning models for supervised and semi-supervised learning tasks using time series. The models include tasks of multi-class classification, one-class classification, representation learning and derivatives. All models are based on PyTorch.

tsai. Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

NFD. Official codebase for the paper "3D Neural Field Generation using Triplane Diffusion"

multitaper. Multitaper codes translated into Python.

A-SOID. An active learning platform for expert-guided, data efficient discovery of behavior.

B-SOID. Behavioral segmentation of open field in DeepLabCut, or B-SOID ("B-side"), is a pipeline that pairs unsupervised pattern recognition with supervised classification to achieve fast predictions of behaviors that are not predefined by users.

mining2021. Code to accompany: https://arxiv.org/abs/2001.08349

DynamicalWassBarycenters_Gaussian. Python

OpenGait. A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.

diffused-heads. Official repository for Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation

EEG-Channel-Interpolation-Using-Deep-Encoder-Decoder-Networks. Code for the paper "EEG Channel Interpolation Using Deep Encoder-decoder Networks"

CNN-EEG. Code for the manuscript "Improved manual annotation of EEG signals through convolutional neural network guidance".

best-toolbox. A Python package for behavioral state analysis using EEG. BEST includes tools automated sleep classification of long-term iEEG data recorded using implantable neural stimulation and recording devices, removal of DBS artifacts and feature extraction.

A-Compact-and-Interpretable-Convolutional-Neural-Network-for-Single-Channel-EEG. In this project, we propose a CNN model to classify single-channel EEG for driver drowsiness detection. We use the Class Activation Map (CAM) method for visualization. Results show that the model not only has a high accuracy but also learns biologically explainable features, e.g., Alpha spindles and Theta burst, as evidence for the drowsy state.

ECG-removal-from-sEMG-by-FCN. ECG ARTIFACT REMOVAL FROM SINGLE-CHANNEL SURFACE EMG USING FULLY CONVOLUTIONAL NETWORKS

eeg-transfer-learning. Source code for self-supervised EEG data transfer learning

DeepEEG. Deep Learning with Tensor Flow for EEG MNE Epoch Objects

Single-Channel-EEG-Denoise. Jupyter Notebook

EEGANet. EEG Artifact Removal Using Deep Learning (source code, IEEE Journal of Biomedical and Health Informatics)

DeepSeparator. Deep learning model for EEG artifact removal

dynamic-spatial-filtering. Code for "Robust EEG processing with dynamic spatial filtering", Banville et al. 2021

FaceQAN. FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration

VTAMIQ. Full-Reference Vision Transformer (ViT)-based IQA method

visual_taste_approximator. Visual Taste Approximator (VTA) is a very simple tool that helps anyone create an automatic replica of themselves that can approximate their own personal visual taste

GeneralizationMetricGAN. Python

data-copying. companion git repository to data-copying paper by Meehan, Chaudhuri, Dasgupta in AISTATS 2020

memorization. Code for "On Memorization in Probabilistic Deep Generative Models"

bias-correction-generative. Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

Sparse-Sharpness-Aware-Minimization. [NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation

hard-prompts-made-easy. Python

fda-geo-out. R

pix2pix-zero. Zero-shot Image-to-Image Translation [SIGGRAPH 2023]

regular-layers. Pytorch modules for linear layers with L1/Nuclear norm regularization

ProxSPS. Polyak step sizes with weight decay in Pytorch

mssim.pytorch. A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.

SWALP. Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".

WASAM. Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)

DiffusionCLIP. [CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models

II2S. Improved StyleGAN Embedding: Where are the Good Latents?

hyperstyle. Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" (CVPR 2022) https://arxiv.org/abs/2111.15666

GANInverter. A GAN inversion toolbox based on PyTorch library. We design a unified pipeline for inversion methods and conduct a comprehensive benchmark.

student_teacher_catastrophic. Investigation of catastrophic forgetting in continual learning using student-teacher framework (MSc Thesis)

Random-Erasing. Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST

LOW. Official Pytorch implementation of "LOW: Training Deep Neural Networks by Learning Optimal Sample Weights"

Attend-and-Excite. Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

xai_tracking. Code for our paper "Explaining Deep Learning Representations by Tracing the Training Process"

pyhopper. PyHopper is a hyperparameter optimizer, made specifically for high-dimensional problems arising in machine learning research.

autoHyper. Python

torchmetrics. Machine learning metrics for distributed, scalable PyTorch applications.

HyperTune. Efficient Hyper-parameter Tuning at Scale

hyperclip. Code repository for the paper "Meta-Learning via Classifier(-free) Diffusion Guidance"

deeptime. Python library for analysis of time series data including dimensionality reduction, clustering, and Markov model estimation

Efficient_SAM. Python

musiclm-pytorch. Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

Text2LIVE. Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)

GSAM. PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)

lowrank_inference. Fitting low-rank RNNs to neural trajectories (LINT method).

mgplvm-pytorch. Jupyter Notebook

warhmm. Python

hierarchical_lfads. Pytorch implementation of lfads, and hierarchical extension

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

lfads-pytorch. PyTorch implementation of the LFADS architecture.

deep_learning_for_dynamical_systems. Python

merging_models. Tests on models merging

BMInf. Efficient Inference for Big Models

enhancing-transformers. An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

glide-finetune. Finetune glide-text2im from openai on your own data.

Principal-Component-Networks. Python

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

MAS-PyTorch. A PyTorch implementation of the ECCV 2018 publication "Memory Aware Synapses: Learning what (not) to forget"

mmdetection. OpenMMLab Detection Toolbox and Benchmark

instruct-pix2pix. Python

grad-cam. [ICCV 2017] Torch code for Grad-CAM

GLIGEN. Open-Set Grounded Text-to-Image Generation

LSUV-pytorch. Simple implementation of the LSUV initialization in PyTorch

Inspect-Embedding-Training. Python script to analyze textual inversion embedding files used with AI image generators

mixout. Implementation of Mixout with PyTorch

mctorch. A manifold optimization library for deep learning

LSUVinit. Reference caffe implementation of LSUV initialization

Quantformer. This is the official pytorch implementation for the paper: *Quantformer: Learning Extremely Low-precision Vision Transformers*.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

clipseg-huggingface. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

clipseg. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

latentblending. Create butter-smooth transitions between prompts, powered by stable diffusion

adapting-CLIP. Python

sd-leap-booster. Fast finetuning using a booster model that puts the initial state to a local minimum

PlotNeuralNet. Latex code for making neural networks diagrams

semantic-image-editing. Python

Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch. [ECCV 2022] Compositional Generation using Diffusion Models

clean-fid. PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

CV_DL_Gather. Gather research papers, corresponding codes (if having), reading notes and any other related materials about Hot🔥🔥🔥 fields in Computer Vision based on Deep Learning.

KeepAugment_Pytorch. :low_brightness:Unofficial PyTorch implementation of KeepAugment

funk-svd. :zap: A python fast implementation of the famous SVD algorithm popularized by Simon Funk during Netflix Prize

face-parsing.PyTorch. Using modified BiSeNet for face parsing in PyTorch

yolact. A simple, fully convolutional model for real-time instance segmentation.

CelebAMask-HQ. A large-scale face dataset for face parsing, recognition, generation and editing.

imgaug. Image augmentation for machine learning experiments.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

prioritized-experience-replay. Prioritized experience replay/importance sampling of mini-batches in supervised learning

finetune-clip-huggingface. Finetuning CLIP on a small image/text dataset using huggingface libs

fer. Facial Expression Recognition with a deep neural network as a PyPI package

paz. Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

py-feat. Facial Expression Analysis Toolbox

acon. Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]

watermark-detection. Model for watermark classification implemented with PyTorch

automatic-watermark-detection. Project for Digital Image Processing

vpt. ❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119

X-Decoder. [CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language

a-large-image-tiler. (Python3, PyQt5) GUI software to tile large images. Designed to image 96-well plates used in wet labs.

FMix. Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'

CARD. Official PyTorch implementation for the paper "CARD: Classification and Regression Diffusion Models"

GradMatch. GradMatch

ricap. Python

ActiveBias. Python

cords. Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

DatasetRefinement-CV. A Survey of Dataset Refinement for Problems in Computer Vision Datasets

ImportanceSampling. Official implementation of "How Important is Importance Sampling for Deep Budgeted Training?"

TERM. Tilted Empirical Risk Minimization (ICLR '21)

RHO-Loss. Python

SelectiveBackPropagation. Implementation of the paper: Selective_Backpropagation from paper Accelerating Deep Learning by Focusing on the Biggest Losers

importance-sampling. Code for experiments regarding importance sampling for training neural networks

AutoLR. AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks

autolrs. Automatic learning-rate scheduler

SVF. [NeurIPS 2022] Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

Felmi. FeLMi: Few-shot Learning with hard Mixup

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

PALAVRA. Python

clipscore. CLIPScore EMNLP code

CLIP-IQA. [AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

UniTune. Implementation UniTune based on stable diffusion

PDF-GAN_pr2023. Official implementation of the PDF-GAN, accepted by Pattern Recognition 2023

direct-inversion. Official code implementation for our paper -- Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models.

Asyrp_official. official repo for Asyrp : Diffusion Models already have a Semantic Latent Space (ICLR2023)

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

PatchDiffusion-Pytorch. Code for the Paper "Improving Diffusion Model Efficiency Through Patching"

patching. Patching open-vocabulary models by interpolating weights

piq. Measures and metrics for image2image tasks. PyTorch.

releasing-research-code. Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

pytorch-msssim. Fast and differentiable MS-SSIM and SSIM for pytorch.

MS_SSIM_pytorch. ms_ssim loss function implemented in pytorch

MS-SSIM_L1_LOSS. Pytorch implementation of MS-SSIM L1 Loss function

Adan. Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

data. A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

clean-code-python. :bathtub: Clean Code concepts adapted for Python

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Deep-learning-in-cloud. List of Deep Learning Cloud Providers

pytorch-lr-finder. A learning rate range test implementation in PyTorch

DiffusionDisentanglement. Official implementation of the paper "Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

prompt-to-prompt. Jupyter Notebook

sd_regularization_images. Pre-Rendered Regularization Images fou use with fine-tuning, especially for the current implementation of "Dreambooth"

pytorch_optimizer. optimizer & lr scheduler & loss function collections in PyTorch

FACIL. Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

fisher-information-matrix. PyTorch implementation of FIM and empirical FIM

ewc. Python

continual-learning-benchmark. Benchmarking continual learning techniques for Human Activity Recognition data. We offer interesting insights on how the performance techniques vary with a domain other than images.

class-incremental-learning. PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).

avalanche. Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

ewc.pytorch. An implementation of EWC with PyTorch

eacl2021-debias-finetuning. Elastic weight consolidation for better bias inoculation

Overcoming-Catastrophic-forgetting-in-Neural-Networks. Elastic weight consolidation technique for incremental learning.

continual-learning. PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

stable-diffusion-aesthetic-gradients. Personalization for Stable Diffusion via Aesthetic Gradients 🎨

point-e. Point cloud diffusion for 3D model synthesis

DIS. This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

MCG_diffusion. Official PyTorch implementation of the NeurIPS 2022 paper "Improving Diffusion Models for Inverse Problems using Manifold Constraints (https://arxiv.org/abs/2206.00941)"

Diffusion-Policies-for-Offline-RL. Python

diffuser. Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

Elastic-Weights-Consolidation. Pytorch implementations of Elastic Weight Consolidation (EWC)

pytorch-ewc. Unofficial PyTorch implementation of DeepMind's PNAS 2017 paper "Overcoming Catastrophic Forgetting"

EWC. Elastic Weight Consolidation in PyTorch

custom-diffusion. Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

deepethogram. Python

textual_inversion. Jupyter Notebook

deep-rl-class. This repo contains the Hugging Face Deep Reinforcement Learning Course.

DeepWebCut. Remake of [DeepLabCut](https://github.com/DeepLabCut/DeepLabCut) for web browsers.

pytorch-fid. Compute FID scores with PyTorch.