Repository accompanying the paper Generative Agents: Interactive Simulacra of Human Behavior, containing the core simulation module for agents that simulate believable human behaviors and their game environment.
Open source
24 alternativesDeep High-Resolution-Net
This repository provides a PyTorch implementation of a CVPR paper on high resolution representations for human pose estimation.
About Deep High-Resolution-Net
Deep High-Resolution-Net is an official PyTorch implementation of the CVPR 2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation." Most earlier pose estimation methods recover high-resolution features from low-resolution ones. This network instead keeps high-resolution representations throughout the whole process, which the authors say produces keypoint heatmaps that are more accurate and spatially precise.
The repository includes code organized into demo, experiments, lib, tools, and visualization folders. The README reports results on the MPII and COCO keypoint datasets for several model variants, including parameter counts, GFLOPs, and accuracy figures. Those MPII results use flip testing and 256x256 input, and the COCO results depend on a detector with a stated human AP.
Key features
- Official PyTorch implementation of the CVPR 2019 human pose estimation paper
- Maintains high-resolution representations through the entire network
- Repeated multi-scale fusion across parallel high-to-low resolution subnetworks
- Reported evaluation results on MPII and COCO keypoint detection datasets
- Demo code for running pose estimation on images
- Visualization code for displaying pose estimation results
Best for: Computer vision researchers and developers who work on human pose estimation and want a reference PyTorch implementation of high-resolution network architectures.
Good for
- Keeps high-resolution representations through the whole network rather than recovering them afterward
- Includes published results on two benchmark datasets with parameter and compute figures
- Open source repository with demo and visualization code
Deep High-Resolution-Net at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Deep High-Resolution-Net alternatives
Tools and sites you could use instead, ranked by how closely they match.
The DeepSeek-R1 repository links to its reasoning research paper and provides related model materials.
Open source
24 alternatives
timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.
Open source
24 alternatives
The learn2learn library supports meta learning experiments and research with PyTorch.
Open source
24 alternatives
MobiLlama is a small language model designed for edge devices, according to its repository description.
Open source
24 alternatives
The GLM-5 repository presents language models for agentic engineering and coding.
Open source
24 alternativesPopular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
Deep High-Resolution-Net FAQ
Which datasets are the reported results based on?
The README reports results on the MPII Human Pose dataset and the COCO keypoint detection dataset (COCO val2017).
Does the repository include demo or visualization code?
Yes. The README notes that demo code was added on 2020/02/01 and that visualization code for showing pose estimation results is included.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.