AzimST
Follow
Lists (1)
Stars
Raspberry Pi PCI Express device compatibility database
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Lane Finding Project for Self-Driving Car ND
Fast, Accurate, Mask-Aware Face Recognition SDK with Liveness Detection
roop extension for StableDiffusion web-ui
Real Time Face Mask Detection using Tensorflow/Keras | Inference on Image, Video and Webcam on ONNX Runtime Environment
Python scripts for performing road segemtnation and car detection using the HybridNets multitask model in ONNX.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Repository for automatic classification and labeling of Urban PointClouds using data fusion and region growing techniques.
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
Function to calculate mAP for set of detected boxes and annotated boxes.
By using Tiny-ML on two separate devices (Arduino Nano 33 BLE Sense, Raspberry Pi), the words we use in the data set are expected to be highly recognized. At the same time, the performance of the …
The goal of Driving Monitoring Systems is to prevent driver-related traffic accidents by detecting the driver's drowsiness, and attention state.
The aim of this project is to analyze the spending behavior of customer groups using various techniques.
The analysis of several vision-based transformers is the main emphasis of this project, which also analyzes their distinctive properties and evaluates how well they work using a common dataset. The…
List of Computer Science courses with video lectures.
Image Processing demos with NumPy and TensorFlow
Break large videos into tiles, magnify those tiles and stitch'em together. Makes large videos processable with low amounts of RAM
An OpenCV/Qt based realtime application for Eulerian Video Magnification / Motion Magnification. Works with multiple videos and cameras at the same time and let's you export the magnified videos.
An unofficial implementation of "Learning-based Video Motion Magnification" in Pytorch.
Eulerian Video Magnification for colors and motions magnification
A collection of algorithms for detecting and handling label noise