Image Stitching algorithm in Python from scratch with gain compensation and blending

Code for the paper Hybrid Spectrogram and Waveform Source Separation

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

Problem Generator for Math Word Prediction

Audio event detection model based on YOLOX

Differentiable IoU of rotated bounding boxes using Pytorch

2020 AI Grand Challenge (3rd track) - public sample

Grand Challenge 4 track 2 sourcecode developed by GIST

Speech Enhancement Generative Adversarial Network

Public dataset developed by KICT_INTFLOW for IITP AI GrandChallenge 2019, Track-3

The world's simplest facial recognition api for Python and the command line

Audio processing by using pytorch 1D convolution network

This is a RNNoise windows demo. It was modified and restructured so that it can be compiled with MSVC, VS2017, VS2019.

Small code snippets that show how to stream camera images to a Coral device.

Convolutional Neural Networks

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usage

Speech Enhancement based on DNN (Spectral-Mapping, TF-Masking), DNN-NMF, NMF

Automagically generate thumbnails, animated GIFs, and summaries from videos

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

Contains samples of GStreamer pipelines and CLI commands for different GStreamer based features (process MPEG2-TS files, get video from DVB, deinterlace video, capture RTSP stream etc.)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Caffe2 is a lightweight, modular, and scalable deep learning framework.