AutoEncoder trained on ImageNet

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

Experiment code for Stochastic Gradient Hamiltonian Monte Carlo

We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs a…

source code for ICLR'23 paper "Non-parametric Outlier Synthesis"

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)

Inference code for Llama models

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

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

An implementation of Deep Canonical Correlation Analysis (DCCA or Deep CCA) with pytorch.

Supplementary code for the paper "Hyperbolic Image Embeddings".

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

[CVPR 2023] Official Pytorch code for Unknown Sniffer for Object Detection: Don’t Turn a Blind Eye to Unknown Objects

The official implementation of Theme Transformer. A Theme-based music generation. IEEE TMM

Muzic: Music Understanding and Generation with Artificial Intelligence

Official Implementation of "Multitrack Music Transformer" (ICASSP 2023)

A PyTorch implementation of DenseNet.

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

source code for ICLR'22 paper "VOS: Learning What You Don’t Know by Virtual Outlier Synthesis"

source code for ICLR'22 paper "VOS: Learning What You Don’t Know by Virtual Outlier Synthesis"

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

A simple and effective method for detecting out-of-distribution images in neural networks.

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

Inference code for facebook LLaMA models with Wrapyfi support

Running large language models on a single GPU for throughput-oriented scenarios.