mc-dropout 开源项目推荐（33 个）

JavierAntoran /Bayesian-Neural-Networks

Pytorch实现Bayes By Backprop、MC Dropout、SGLD、Local Reparamentrization Trick、KF-Lapplace、SG-HMC等

alexrakowski /mc-dropout-mnist

Implementation of the MNIST experiment for Monte Carlo Dropout from http://mlg.eng.cam.ac.uk/yarin/PDFs/NIPS_2015_bayesian_convnets.pdf

kenya-sk /mc_dropout_tensorflow

This repository reimplemented "MC Dropout" by tensorflow 2.0 Eager Extension.

ronaldseoh /ronald_bdl

An experimental Python package for learning Bayesian Neural Network.

ronaldseoh /DropoutUncertaintyExps

(Forked Version) Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"

ratschlab /uncertainty-vst-2026

Code for "Probabilistic uncertainty in virtual spatial transcriptomics from histology is largely redundant with the predicted mean" (bioRxiv 2026). Benchmark of aleatoric and epistemic uncertainty (Gaussian/Poisson/NB heads, deep ensembles, MC dropout, Laplace) for gene expression predicted from H&E on 10x Visium.

eismont21 /knowledge-surrogate-opt

A transformative approach to manufacturing optimization, focusing on the textile forming process. This research synergizes domain-specific knowledge with simulation modeling and introduces Bayesian optimization for efficient parameter space exploration.

Leorhh /Tf_mab

Transformer-based reward modeling with adaptive exploration for multi-armed bandit recommendation

Islamomar-1 /ActiveScreen

Active learning framework for high-throughput virtual screening — GIN surrogate model with MC-Dropout uncertainty, Thompson Sampling acquisition, and plug-in docking oracles (QED mock · AutoDock Vina · Glide). Recovers >95% of top-1% hits while docking only ~6% of the library. Based on Graff, Shakhnovich & Coley, Chem. Sci. 2021.

Animesh-Kr /oct-fluid-segmentation

Attention-Guided TransUNet for multi-class retinal fluid segmentation in OCT with MC Dropout uncertainty quantification

wishalfatima /Bayesian-Deep-Learning

Implementation of MC-Dropout and Deep Ensembles for uncertainty estimation in regression (UCI Energy) and classification (Fashion-MNIST) tasks. Includes OOD detection with notMNIST.

GISCheng /uncertainty_explanation

Demo codes and data for a published work "Uncertainty explanation of artificial intelligence models by SHAP"

cplou99 /BayesianDL

We provide two notebooks that enable users to explore and experiment with some BDL techniques as Ensembles, MC Dropout and Laplace Approximation. In this way, they allow you to intuitively visualize the main differences among them in a Simulated Dataset and Boston Dataset.

Ganmaxxx /mc-dropout-medical-uncertainty

PyTorch implementation of Last-Layer MC Dropout for epistemic uncertainty estimation in Medical AI. Automatically identifies clinical edge cases and label noise in chest X-rays.

Nahilel /DiffSepsis

DiffSepsis: Semi-supervised conditional time-series diffusion (Diffusion-TS, ICLR 2024) with Bayesian epistemic uncertainty (MC Dropout) for reliable early sepsis detection on PhysioNet 2019 under extreme label scarcity.

uchicago-dsi-bayesianml /wi26-turbofan-rul

Example project (Winter 2026): Bayesian change-point detection, a hierarchical PyMC model, Kalman filters and MC dropout for jet-engine remaining useful life on NASA C-MAPSS, with a candid staff review

uchicago-dsi-bayesianml /wi26-pedestrian-trajectory-uncertainty

Example project (Winter 2026): pedestrian trajectory prediction on ETH/UCY with an LSTM, MC dropout and a Pyro variational output layer, with a candid staff review

AayuShen /SCoPe-Trust-Region-Latent-Planning

SCoPe: per-step trust scores for planning with a frozen JEPA world model (DINO-WM). 22AIE401 Reinforcement Learning term project, Amrita School of Computing.

uchicago-dsi-bayesianml /wi26-deepfake-uncertainty

Example project (Winter 2026): deepfake image detection on Deepfake-Eval-2024 with MC dropout and a variational linear head on frozen Xception features, with a candid staff review

Kaleidophon /tenacious-toucan

Master thesis for the MSc. Artificial Intelligence at the Universiteit van Amsterdam, 2019