Simon Donike's starred repositories
private-gpt
Interact with your documents using the power of GPT, 100% privately, no data leaks
latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
techniques
Techniques for deep learning with satellite & aerial imagery
PerceptualSimilarity
LPIPS metric. pip install lpips
Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
EDSR-PyTorch
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
a-PyTorch-Tutorial-to-Super-Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution
DiffusionFastForward
DiffusionFastForward: a free course and experimental framework for diffusion-based generative models
SRCNN-pytorch
PyTorch implementation of Image Super-Resolution Using Deep Convolutional Networks (ECCV 2014)
albumentations_examples
Augmentations usage examples for albumentations library
syndata-generation
Code used to generate synthetic scenes and bounding box annotations for object detection. This was used to generate data used in the Cut, Paste and Learn paper
worldstrat
The WorldStrat Dataset
super-image
Image super resolution models for PyTorch.
pytorch-super-resolution-model-collection
Collection of Super-Resolution models via PyTorch
highresnet
PyTorch implementation of HighRes3DNet
Generative-Models
Repository of Various Test & Implementation of Generative Models
Ship-Detection-from-Satellite-Images-using-YOLOV4
Ship detection from remote sensing imagery is a crucial application for maritime security which includes among others traffic surveillance, protection against illegal fisheries, oil discharge control and sea pollution monitoring. This is typically done through the use of an Automated Identification System (AIS), which uses VHF radio frequencies to wirelessly broadcast the ships location, destination and identity to nearby receiver devices on other ships and land-based systems. AIS are very effective at monitoring ships which are legally required to install a VHF transponder, but fail to detect those which are not, and those which disconnect their transponder. So how do you detect these uncooperative ships? This is where satellite imagery can help. Synthetic Aperture Radar (SAR) imagery uses radio waves to image the Earth’s surface. Unlike optical imagery, the wavelengths which the instruments use are not affected by the time of day or meteorological conditions, enabling imagery to be obtained day or night, with cloudy, or clear skies. Satellites are collecting these images which could be used to make algorithms for ship detection and segmentation.
opensr-test
A comprehensive benchmark for real-world Sentinel-2 imagery super-resolution
CodeMonkeys
CodeMonkeys project for Dracco Hackaton at Manresa
remicres.github.io
Personal web site