PyTorch

zheyemuchrooms/zheye

A convolutional neural network program that identifies inverted Chinese character captchas used by Zhihu for login verification.

HyenaDNAHazyResearch/hyena-dna

A long-range genomic foundation model that processes DNA sequences up to 1 million nucleotides at single nucleotide resolution.

PyTorch Framepyg-team/pytorch-frame

A modular deep learning framework for PyTorch to build neural networks on heterogeneous tabular data.

ChemicalXAstraZeneca/chemicalx

A PyTorch and TorchDrug based deep learning library for drug pair scoring, predicting interactions, side effects, and synergy.

Anti-UAVZhaoJ9014/Anti-UAV

A benchmark and toolkit for discovering, detecting, recognizing, and tracking UAVs in the wild using RGB and thermal infrared video.

DNABERTjerryji1993/DNABERT

A pre-trained BERT model designed for DNA sequence analysis, enabling genome understanding tasks like classification and motif discovery.

OpenChemMariewelt/OpenChem

A deep learning toolkit for computational chemistry and drug design research with PyTorch backend.

gpdatenpas/gpd

Detects 6-DOF grasp poses for parallel jaw grippers in 3D point clouds, enabling robotic grasping of novel objects in clutter.

TAPE (Tasks Assessing Protein Embeddings)songlab-cal/tape

A benchmark for evaluating protein language models through five biologically relevant semi-supervised learning tasks.

UNImahmoodlab/UNI

A vision transformer foundation model pre-trained on over 200 million pathology images for computational pathology tasks.

CrowdNavvita-epfl/CrowdNav

A deep reinforcement learning framework for crowd-aware robot navigation using attention mechanisms to model human-robot and human-human interactions.

semantic_slamfloatlazer/semantic_slam

Real-time 3D semantic mapping system using a handheld RGB-D camera, built on ROS with ORB_SLAM2 and PSPNet.

HoVer-Netvqdang/hover_net

A PyTorch-based deep learning model for simultaneous nuclear instance segmentation and classification in histopathology images.

CHIEFhms-dbmi/CHIEF

A general-purpose foundation model for cancer diagnosis and prognosis prediction from histopathology whole-slide images.

MicroSAMcomputational-cell-analytics/micro-sam

Interactive segmentation and tracking tools for microscopy images built on Segment Anything.

3d-vehicle-trackingucbdrive/3d-vehicle-tracking

Official PyTorch implementation for joint monocular 3D vehicle detection and tracking from ICCV 2019.

GitHub repositoryPRBonn/LiDAR-MOS

A learning-based approach for moving object segmentation in 3D LiDAR data, distinguishing moving vs. static objects in real-time.

EvoDiffmicrosoft/evodiff

A diffusion framework for controllable protein sequence and evolutionary alignment generation using discrete diffusion models.

Lucentgreentfrapp/lucent

A PyTorch adaptation of Lucid for visualizing and interpreting neural networks through feature visualization.

Detecto - Train and run object detection models with 5-10 lines of codealankbi/detecto

Build fully-functioning computer vision and object detection models with PyTorch in just 5 lines of code.

OmegaFoldHeliXonProtein/OmegaFold

High-resolution de novo protein structure prediction from amino acid sequences using deep learning.

GigaPathprov-gigapath/prov-gigapath

A whole-slide foundation model for digital pathology, pre-trained on real-world data to analyze tissue slides at tile and slide levels.

PyTouneGRAAL-Research/poutyne

A simplified Keras-like framework for PyTorch that reduces boilerplate code for training neural networks.

JTVAEwengong-jin/icml18-jtnn

A junction tree variational autoencoder for generating valid molecular graphs with desired chemical properties.

DDADTRI-ML/DDAD

A benchmark dataset for long-range (up to 250m) dense depth estimation in autonomous driving, featuring 360° LiDAR ground truth.

TensorLayerXtensorlayer/TensorLayerX

A unified deep learning and reinforcement learning framework supporting multiple backends and hardware platforms.

LEDNetxiaoyufenfei/LEDNet

A lightweight encoder-decoder neural network for real-time semantic segmentation on resource-constrained devices.

DeepSlideBMIRDS/deepslide

A sliding window framework for classifying high-resolution whole-slide microscopy and histopathology images using deep neural networks.

Lightwoodmindsdb/lightwood

An AutoML framework that generates and customizes machine learning pipelines using declarative JSON-AI syntax.

CONCHmahmoodlab/CONCH

A vision-language foundation model for computational pathology, pretrained on 1.17M histopathology image-caption pairs for diverse AI tasks.

DL Translatexhlulu/dl-translate

A Python library for translating between 200 languages using Hugging Face transformer models like mBART-50, m2m100, and NLLB-200.

ChemBERTa-2seyonechithrananda/bert-loves-chemistry

A collection of BERT-like transformer models pre-trained on chemical SMILES data for drug design and property prediction.

SA-SSDskyhehe123/SA-SSD

A single-stage 3D object detector for point clouds that improves localization precision by explicitly leveraging structure information.

DNABERT-2Zhihan1996/DNABERT_2

A foundation model for multi-species genome understanding, achieving state-of-the-art performance on 28 genomic tasks.

Archaimicrosoft/archai

A Python library for fast, reproducible, and modular Neural Architecture Search (NAS) to generate efficient deep networks.

PaperRobot: Incremental Draft Generation of Scientific IdeasEagleW/PaperRobot

An AI system that incrementally generates scientific paper drafts by predicting links between concepts and generating text sections.