Subhasis Chakraborty's repositories
ai_developers_day_2019
this repository is for the NVIDIA AI Developers Day 2019 at South Korea
albumentations
fast image augmentation library and easy to use wrapper around other libraries
awesome-youtubers
▶️ An awesome list containing awesome YouTubers that teach about technology.
build-your-own-x
🤓 Build your own (insert technology here)
darknet_face_with_landmark
加入关键点的darknet训练框架，使用yolov3实现了轻量级的人脸检测
deep-vision
Learning and replicating famous deep learning models for computer vision tasks
digital_video_introduction
A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding).
faster-mobile-retinaface
Reimplementation of retinaface, faster and stronger.
LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices
A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......
libfacedetection
An open source library for face detection in images. The face detection speed can reach 1500FPS.
lowlevelprogramming-university
How to be low-level programmer
mmdetection_lite
基于mmdetection实现一些轻量检测方法(thundernet etc.)
mobilenetv2-yolov3
yolov3 with mobilenetv2 and efficientnet
motioneye
A web frontend for the motion daemon.
MTCNN_Tutorial
As a series of tutorials on the most popular deep learning algorithms for new-entry deep learning research engineers, MTCNN has been widely adopted in industry for human face detection task which is an essential step for subsquential face recognition and facial expression analysis. This tutorial is designed to explain how to implement the algorithm. In this tutorial, developers will learn how to build MTCNN model for face detection task.
OpenLabeling
Label images and video for Computer Vision applications
python-can
The can package provides controller area network support for Python developers
PyTorch_ONNX_TensorRT
A tutorial about how to build a TensorRT Engine from a PyTorch Model with the help of ONNX
Real-time-human-pose-estimation-by-pytorch
A reimplementation of real time human pose estimation using Pytorch. Both CMU's original model and mobilenet backbone are provided. The code is optimized for a faster inference time !
road-scene-infrared-visible-images
Datasets: road-scene-infrared-visible-images, for feature matching, image registration, and image fusion
segmentation_models
Segmentation models with pretrained backbones. Keras.
VALI
Video processing in Python
volksdep
volksdep is an open-source toolbox for deploying and accelerating PyTorch, Onnx and Tensorflow models with TensorRT.
wtfpython
What the f*ck Python?