tersekmatija
Interested in ML, CS, maths, and data science. Master of Computer and Data Science
ML Engineer @ LuxonisSlovenia
Pinned Repositories
depthai
DepthAI Python API utilities, examples, and tutorials.
depthai-experiments
Experimental projects we've done with DepthAI.
Bayesian-CSRNet
Bayesian-CSRNet
eWaSR
An embedded-compute-ready maritime obstacle detection network eWaSR.
lwcc
LWCC: A LightWeight Crowd Counting library for Python that includes several pretrained state-of-the-art models.
mobileone
MobileOne - An Improved One millisecond Mobile Backbone. Unofficial Pytorch implementation for edge export - ONNX, OpenVINO.
RealtimeStereo
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
strawberry-detection
PyTorch reimplementation of YOLOP for strawberry detection
tersekmatija's Repositories
tersekmatija/lwcc
LWCC: A LightWeight Crowd Counting library for Python that includes several pretrained state-of-the-art models.
tersekmatija/eWaSR
An embedded-compute-ready maritime obstacle detection network eWaSR.
tersekmatija/mobileone
MobileOne - An Improved One millisecond Mobile Backbone. Unofficial Pytorch implementation for edge export - ONNX, OpenVINO.
tersekmatija/Bayesian-CSRNet
Bayesian-CSRNet
tersekmatija/RealtimeStereo
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
tersekmatija/lwcc_weights
Lightweight Crowd Counting Weights
tersekmatija/strawberry-detection
PyTorch reimplementation of YOLOP for strawberry detection
tersekmatija/Bayesian-Crowd-Counting
Official Implement of ICCV 2019 oral paper Bayesian Loss for Crowd Count Estimation with Point Supervision
tersekmatija/crowd-counting-cnns
Paper on CNN crowd counting approaches for IBB master's course at FRI, Ljubljana
tersekmatija/crowd-counting-scnn
This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-convolutional neural network and uses an expert CNN that chooses the best crowd density CNN regressor for parts of the scene from a bag of regressors. This helps it tackle intra-scene crowd density variation and obtain SOTA results
tersekmatija/CROWD-COUNTING-USING-CSRNET
tersekmatija/CSRNet-keras
Implementation of the CSRNet paper (CVPR 18) in keras-tensorflow
tersekmatija/CSRNet-pytorch
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
tersekmatija/depthai-experiments
Experimental projects we've done with DepthAI.
tersekmatija/depthai-ml-training
Some Example Neural Models that we've trained along with the training scripts
tersekmatija/DM-Count
Code for NeurIPS 2020 paper: Distribution Matching for Crowd Counting.
tersekmatija/ERK-2020
A review and comparison of time series similarity measures
tersekmatija/mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
tersekmatija/mscnn
mscnn crowd counting model implementation, source from "Multi-scale Convolution Neural Networks for Crowd Counting" write by Zeng L, Xu X, Cai B, et al.
tersekmatija/onnx
Open standard for machine learning interoperability
tersekmatija/re-LearningToCountEverything
Learning To Count Everything Reproducibility Challenge
tersekmatija/Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
tersekmatija/SFANet-crowd-counting
This is an unofficial implement of the arXiv paper Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting by PyTorch.
tersekmatija/sganet-crowd-counting
A Pytorch implementation of SGANet for crowd counting
tersekmatija/tersekmatija.github.io
Personal Website