Guillaume Mougeot

mini_metrics. Evaluation workflow for hierarchical classifiers

AwesomeAnalysisTools. An awesome list of tools that can be used to explore and analyse both traditional and computer vision biodiversity records

embeddoor. Python

gemini_segment. A demo for segmentation via the Gemini API using Nano Banana Pro

cluster_partition. A simple script to cluster test/training sets based on unsupervised clustering

PlantBERT. Learning the syntax of plant assemblages

camtrap-dp. Camera Trap Data Package (Camtrap DP)

Mothbox. Developing an open source,low cost automated system for Moth-Lighting photography

termux-app. Termux - a terminal emulator application for Android OS extendible by variety of packages.

ioio. Software, firmware and hardware of the IOIO - I/O for Android

annflux. A research tool for exploring and annotating large datasets with Active Learning

insectai. Testing Camtrap DP for InsectAI data

insect-detect-night. Detection models and Python scripts for automated insect monitoring with the Insect Detect DIY camera trap.

llm-mind-map. A mind map on Large Language Models (LLMs). This can be a useful reference or learning guide for both beginners and experts alike.

bia-bob. BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.

CountGD. Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

replicAnt. replicAnt - generating annotated images of animals in complex environments with Unreal Engine

insect-detect. Software for automated insect monitoring with the Insect Detect camera trap.

insect-detect-docs. Source files and assets of the documentation website for the Insect Detect DIY camera trap for automated insect monitoring.

InsectFoundationModel. Insect Foundation AI Model and Dataset for Precision Agriculture

unmaintainable-code. A more maintainable, easier to share version of the infamous http://mindprod.com/jgloss/unmain.html

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

cupynumeric. NumPy and SciPy on Multi-Node Multi-GPU systems

BioEncoder. Python

anylabeling. Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

BiodivX-XPRIZE-ML-Pipeline. Simple repository for managing the overall CV ML execution pipeline of the ETH BiodivX for the XPRIZE Rainforest competition finals.

pyremotedata. This repository contains the python module "pyRemoteData" which handles high-bandwidth data transfer with LFTP.

SimpleClick. SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)

gbif-dl. GBIF classification dataloaders

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

aldi. Align and Distill: Unifying and Improving Domain Adaptive Object Detection (TMLR Featured 2025)

BIOSCAN-1M. A dataset of 1M insect specimens with DNA barcodes, taxonomy, and images.

TRUEFAD. TRUE Fiber Atrophy Distinction

cupy. NumPy & SciPy for GPU

dexp. Dataset EXploration & Processing

napari-biom3d. Python

pyxu. Modular and scalable computational imaging in Python with GPU/out-of-core computing.

biom3d. Easy Volumetric Segmentation with Deep Learning

micro-sam. Segment Anything for Microscopy

TEST.

patchly. A grid sampler for larger-than-memory N-dimensional images

unetr_plus_plus. [IEEE TMI-2024] UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation

napari-sam. Segment anything with our Napari integration of Meta AI's Segment Anything Model (SAM)!

taichi. Productive, portable, and performant GPU programming in Python.

CLIP-Driven-Universal-Model. [ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

stable-diffusion. A latent text-to-image diffusion model

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

unetgan. Official Implementation of the paper "A U-Net Based Discriminator for Generative Adversarial Networks" (CVPR 2020)

stylegan2-ada-pytorch. StyleGAN2-ADA - Official PyTorch implementation

AVAE. Python

Controlling-generative-models-with-continuous-factors-of-variations. Recent deep generative models are able to provide photo-realistic images as well as visual or textual content embeddings useful to address various tasks of computer vision and natural language processing. Their usefulness is nevertheless often limited by the lack of control over the generative process or the poor understanding of the learned representation. To overcome these major issues, very recent work has shown the interest of studying the semantics of the latent space of generative models. In this paper, we propose to advance on the interpretability of the latent space of generative models by introducing a new method to find meaningful directions in the latent space of any generative model along which we can move to control precisely specific properties of the generated image like the position or scale of the object in the image. Our method does not require human annotations and is particularly well suited for the search of directions encoding simple transformations of the generated image, such as translation, zoom or color variations. We demonstrate the effectiveness of our method qualitatively and quantitatively, both for GANs and variational auto-encoders.

c_from_python. Calling C from Python

research-contributions. Implementations of recent research prototypes/demonstrations using MONAI.

stackview. Interactive image stack viewing in jupyter notebooks based on ipycanvas and ipywidgets

SSL4MIS. Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

google-research. Google Research

fvcore. Collection of common code that's shared among different research projects in FAIR computer vision team.

MedMNIST. [pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification

BenchmarkTransferLearning. Official PyTorch Implementation and Pre-trained Models for Benchmarking Transfer Learning for Medical Image Analysis

ContIG. This is the official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

DiRA. Official PyTorch Implementation for DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis - CVPR 2022

pytorch_GAN_zoo. A mix of GAN implementations including progressive growing

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

msn. Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)

suncet. Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803

DenoiSeg. Joint training of denoising and segmentation.

ubuntu-slurm. Steps to create a small slurm cluster with GPU enabled nodes

napari. napari: a fast, interactive, multi-dimensional image viewer for python

panda3d. Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU

magicgui. build GUIs from type annotations

SCF. Spherical Confidence Learning for Face Recognition, accepted to CVPR2021 (Oral).

statannotations. add statistical significance annotations on seaborn plots. Further development of statannot, with bugfixes, new features, and a different API.

EvaluateSegmentation. A program to evaluate the quality of image segmentations.

pyimagej. Use ImageJ from Python

miseval. a metric library for Medical Image Segmentation EVALuation

mc-dc. Demonstration code for Marching Cubes and Dual Contouring

napari-annotator. A lightweight plugin extending label layer control.

nnFormer. Python

simple-omero-client. Maven project to easily connect to OMERO.

rising. Provides everything needed for high performance data loading and augmentation in pytorch.

torchio. Medical imaging processing for AI applications.

ModelsGenesis. [MICCAI 2019 Young Scientist Award] [MEDIA 2020 Best Paper Award] Models Genesis, one of the first "foundation" models in medical image analysis for multiple downstream tasks

napari-accelerated-pixel-and-object-classification. GPU-accelerated, OpenCL-based Random Forest Classifiers for pixel and labeled object classification in napari.

pyclesperanto_prototype. GPU-accelerated bio-image analysis focusing on 3D+t microscopy image data

self-supervised-3d-tasks. Python

kaibu. Kaibu -- a progressive web app for visualizing and annotating multi-dimensional images.

triton. Development repository for the Triton language and compiler

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

omero-user-scripts. Plugins for OMERO

cytoself. Self-supervised models for encoding protein localization patterns from microscopy images

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

cool-papers-in-pytorch. Reimplementing cool papers in PyTorch...

bonapity. Get a simple HTTP (REST) API with only this simple decorator : @bonapity !

podofo. A simple pdf search engine with flask

scene_detection. Trying to detect generic from several episodes of series to delete them automatically, using perceptual hash...

Pytorch-FaceNet-DogDataset. Paper To Code implementation of Facenet in native pytorch on Dog Dataset

moco-v3. PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

sacred. Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

volo. VOLO: Vision Outlooker for Visual Recognition

vision_transformer. Jupyter Notebook

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

batchgenerators. A framework for data augmentation for 2D and 3D image classification and segmentation

NuSeT. NuSeT: A Deep Learning Tool for Reliably Separating and Analyzing Crowded Cells

flax. Flax is a neural network library for JAX that is designed for flexibility.

convit. Code for the Convolutional Vision Transformer (ConViT)

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

alphafold. Open source code for AlphaFold 2.

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

pytorch-optimizer. torch-optimizer -- collection of optimizers for Pytorch

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

knodle. A PyTorch-based open-source framework that provides methods for improving the weakly annotated data and allows researchers to efficiently develop and compare their own methods.

pytorch_active_learning. PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book

deepBlink. Threshold independent detection and localization of diffraction-limited spots.

alias-free-gan. Alias-Free GAN project website and code

CL-Gym. CL-Gym: Full-Featured PyTorch Library for Continual Learning

deit. Official DeiT repository

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Intelligent-Pixel-Annotation-Tool. A web based interactive image annotation tool.

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

SegLossOdyssey. A collection of loss functions for medical image segmentation

vuba. An easy to use library for constructing OpenCV HighGUI interfaces.

medicaldetectiontoolkit. The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

Image_Segmentation. Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

libpointmatcher. An Iterative Closest Point (ICP) library for 2D and 3D mapping in Robotics

QCANet. Convolutional Neural Network-Based Instance Segmentation Algorithm to Acquire Quantitative Criteria of Early Mouse Development

mmsegmentation. OpenMMLab Semantic Segmentation Toolbox and Benchmark.

mmcv. OpenMMLab Computer Vision Foundation

HRNet-Semantic-Segmentation. The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

openseg.pytorch. The official Pytorch implementation of OCNet, OCRNet, and SegFix.

Lite-HRNet. This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

caffe-unet-docker. The U-Net Segmentation server (caffe_unet) for Docker

DSB_2018. Python

tensorflow. An Open Source Machine Learning Framework for Everyone

awesome-cell-detection-segmentation. nucleus/cell and histopathology image classification,detection,segmentation

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

mmdetection. OpenMMLab Detection Toolbox and Benchmark

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

AdelaiDet. AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

tensorpack. A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

seq_ppi. This is the repository for PIPR. This repository contains the source code and links to some datasets used in the ISMB/ECCB-2019 paper "Multifaceted Protein-Protein Interaction Prediction Based on Siamese Residual RCNN".

2018DSB. 2018 Data Science Bowl 2nd Place Solution

hiddenlayer. Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

cellpose. a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

FISHcount. Software for counting single RNA molecules using analysis of FISH data

nnUNet. Python

imjoy-interactive-segmentation. Python

imjoy-starter. Jupyter Notebook

webknossos. Visualize, share and annotate your large 3D images online

tf-resnet-cifar10. TensorFlow implementation of ResNet-110 tested on CIFAR10

pymia. pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis

pytorch_resnet_cifar10. Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

stardist. StarDist - Object Detection with Star-convex Shapes

tanda. Learning to Compose Domain-Specific Transformations for Data Augmentation

dsb2018_topcoders. DSB2018 [ods.ai] topcoders

open-solution-data-science-bowl-2018. Open solution to the Data Science Bowl 2018

sonnet. TensorFlow-based neural network library

SketchUp-IFC-Manager. IFC data manager and exporter for SketchUp.

gaphas. Gaphas is the diagramming widget library for Python.

pygubu. A simple GUI builder for the python tkinter module

ScpToolkit. Windows Driver and XInput Wrapper for Sony DualShock 3/4 Controllers

Cutout. 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552

tensor2tensor. Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

shake-shake. 2.86% and 15.85% on CIFAR-10 and CIFAR-100

SJTUThesis. 上海交通大学 LaTeX 论文模板 | Shanghai Jiao Tong University LaTeX Thesis Template

tpu. Reference models and tools for Cloud TPUs.

RelativisticGAN. Code for replication of the paper "The relativistic discriminator: a key element missing from standard GAN"

handson-ml2. ⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.

Deformable-ConvNets. Deformable Convolutional Networks

insightface. State-of-the-art 2D and 3D Face Analysis Project

KENN. KENN: Knowledge Enhanced Neural Networks

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

stylegan. StyleGAN - Official TensorFlow Implementation

tensornets. High level network definitions with pre-trained weights in TensorFlow

keras-tqdm. Keras integration with TQDM progress bars

tensorflow-triplet-loss. Implementation of triplet loss in TensorFlow

Keras-OpenFace. Keras-OpenFace is a project converting OpenFace from Torch implementation to a Keras version

models. Models and examples built with TensorFlow