Mike's Projects
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
behavioral-cloning
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
📃 PyTorch Implementation of DA-RNN (arXiv:1704.02971)
Torchreid: Deep learning person re-identification in PyTorch.
An introduction to graph convolutional neural networks with PyTorch Geometric
A minimalistic example on how to use LSTMs for time series predictions
Flight delay prediction based on the 2007 entries from the US domestic flight database
California housing price prediction with NN, Random Forest and Linear Regression
Predicting total battery cycle life time with machine learning
Tutorials for signal prediction with LSTM networks in keras
Map maker achitecture for a Robosoft Kompai robot placed in the simulated factory environment of MRDS
Add index number to markdown header
OpenMMLab Video Perception Toolbox. It supports Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Detection (VID) with a unified framework.
Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
:bar_chart: Benchmark multiple object trackers (MOT) in Python
StrongSORT: Make DeepSORT Great Again
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
Real-time multi-person tracker using YOLO v3 and deep sort