Muhammad Maaz's Projects
A new framework for open-vocabulary object detection, based on maskrcnn-benchmark
(CVPR 2021 Oral) Open World Object Detection
This repository contains the Physics tests to prepare for BISE Lahore matriculation and inter examinations
The source code for 17 days crash course by Pyimagesearch
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
A PyTorch toolkit for 2D Human Pose Estimation.
Pytorch implementation of "Stacked Hourglass Networks for Human Pose Estimation"
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.
This repository contains two different methods to skip frames using OpenCV. It also provides speed comparison of two methods.
This repository implements the social distancing violation detection to reduce the spread of COVID-19 and other diseases by ensuring social distancing in public places, shopping malls, hospitals and restaurants.
Official PyTorch implementation of the paper: "Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results" (2022)
A PyTorch implementation of SSDLite on COCO
Self-Supervised Learning for Fine-Grained Image Categorization
This repository contains simple python packages for DNN training.
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
Implementation Thundernet
UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
This repository contains training and inference pipelines for Object Detection model yolov3.
YoloV3 Implemented in Tensorflow 2.0