markpp

object_detectors

autoencoders

deep-learning-course

deepstream_dockers

A project demonstrating how to make DeepStream docker images.

diffusion-point-cloud

:thought_balloon: Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

dift

[NeurIPS'23] Emergent Correspondence from Image Diffusion

dockers

A collection of dockerfiles and scripts

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

GeoSeg

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image and UAV image segmentation.

Graph-Neural-Networks

GPU_monitoring

Monitoring computers/GPU usage

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

keypoint-detection

2D keypoint detection with Pytorch Lightning and wandb

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

MAE

PyTorch implementation of Masked Autoencoder

MAE-pytorch

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

markpp.github.io

Blog, on a PhD in robotics, based on Pelican.

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

object-detection

This is an ongoing project of designing a custom object detector from scratch. You can also use the pytorch-lightning training pipeline to train your own model.

pl_bolts

Pytorch Lightning implementations of different deep learning model along with various data modules

point-cloud-exercises

Exercises for Point Cloud lecture

PoseFromPointClouds

Tensorflow and Pytorch implementations for pose predictions from point clouds.

poster-generator

Generating poter of freshly graduated PhD students from AAU Visual Analysis and Perception

ros2_deepstream

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

segmentation_models.pytorch

Segmentation models with pretrained backbones. PyTorch.

sewer_autoencoders

Autoencoder implementations for analysis of sewer inspection images

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

thermal_autoencoder

torch2trt

An easy to use PyTorch to TensorRT converter