VeriSilicon/acuity-models
Acuity Model Zoo
This project offers a collection of pre-trained AI models ready for use in various applications. It takes raw data, like images or audio, and processes it to perform tasks such as identifying objects, translating speech, or improving image quality. This is ideal for embedded systems developers or AI engineers who need to quickly integrate advanced AI capabilities into hardware powered by Vivante NPU IP.
152 stars.
Use this if you are developing AI-powered applications for Vivante NPU IP hardware and need a wide array of pre-optimized models for tasks like image classification, object detection, or natural language processing.
Not ideal if you are looking for a general-purpose AI model library for cloud or non-embedded CPU/GPU environments, or if you need to train models from scratch on custom datasets.
Stars
152
Forks
24
Language
JavaScript
License
—
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VeriSilicon/acuity-models"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lutzroeder/netron
Visualizer for neural network, deep learning and machine learning models
mert-kurttutan/torchview
torchview: visualize pytorch models
raghakot/keras-vis
Neural network visualization toolkit for keras
janosh/diagrams
Diagrams of concepts in physics/chemistry/ML
dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!