A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
-
Updated
Jun 21, 2024 - Python
A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
PyTorch (from scratch) implementation and training of HigherHRNet.
OpenMMLab Pose Estimation Toolbox and Benchmark.
Code for the paper: Soft labelling for budget-constrained semantic segmentation: Bringing coherence to label down-sampling
More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam,dcn and so on), and tensorrt
A lightweight pytorch implementation of HRNet human pose estimation
A free Blender 3D multi-camera mocap solution.
UTRNet: High-Resolution Urdu Text Recognition In Printed Documents (ICDAR'23)
Fast and accurate Human Pose Estimation using ShelfNet with PyTorch
This repository contains code to detect (track) landmark.
Keypoint detection. Launch on RK3588. Training custom models.
A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
tensorflow implementation for "High-Resolution Representations for Labeling Pixels and Regions"
This repository is for MORAI dataset training in semantic segmentation with HRNet + OCR
Multi-person Human Pose Estimation with HRNet in Pytorch
Multi-person Human Pose Estimation with HigherHRNet in Pytorch, with TensorRT support
This is a CPM-HRNet-combined model that outperforms the SOTA HRNet model by adding additional self-designed lightweight HRNets with intermediate supervisions after the original HRNet architecture.
Add a description, image, and links to the hrnet topic page so that developers can more easily learn about it.
To associate your repository with the hrnet topic, visit your repo's landing page and select "manage topics."