Name: Aldo von Wangenheim
Type: User
Company: INCoD/UFSC
Bio: Aldo v.Wangenheim has R&D experience in the areas of Autonomous Vehicular Navigation, Computer Vision/Image Analysis and Processing and Health Informatics.
Twitter: awangenh
Location: Florianópolis, Santa Catarina Island
Blog: http://www.inf.ufsc.br/~aldo.vw
Aldo von Wangenheim's Projects
3D ResNets for Action Recognition (CVPR 2018)
Temporal Segments LSTM and Temporal-Inception for Activity Recognition
Python implementation of minimizing the mumford-shah functional for piecewise smooth image approximation.
Automatic installer scripts for DeOldify
Paper list for multiple object tracking
TCDL 2018 Workshop: Introduction to Image Processing with Python and Jupyter Notebooks
Experiments with the Generalized Hough transform.
More experiments with the Generalized Hough Transform.
Compact Generalized Non-local Network (NIPS 2018)
Reverse engineered ChatGPT API
Let us control diffusion models!
The 3rd edition of course.fast.ai
Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition
Simple example of using a CSI-Camera (like the Raspberry Pi Version 2 camera) with the NVIDIA Jetson Nano Developer Kit
Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
Simple Online Realtime Tracking with a Deep Association Metric
A Deep Learning based project for colorizing and restoring old images (and video!)
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
fast-stable-diffusion + DreamBooth
The fastai deep learning library, plus lessons and tutorials
Fast anisotropic diffusion filter (2D and 3D)
Draft of the fastai book
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow