The PyVisionAI Official Repo

A hands-on collection of foundational computer vision projects for everyone.

Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta

This is an official repository for "Harnessing Vision Models for Time Series Analysis: A Survey".

A simple to use package to call various model providers such as openai, anthropic, and others with utmost reliability, security, and performance.

Implementation of Midas from [Towards Robust Monocular Depth Estimation] in Pytorch and Zeta

we generate captions to the images which are given by user(user input) using prompt engineering and Generative AI

Enhance your skills in prompt engineering for vision models. Learn to effectively prompt, fine-tune, and track experiments for models like SAM, OWL-ViT, and Stable Diffusion 2.0 to achieve precise image generation, segmentation, and object detection.

An implementation of gated MLPs in tinygrad, as an alternative to transformers.

[CVPR 2025] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

General Vision Model Training Template

A framework to compute threshold sensitivity of deep networks to visual stimuli.

In This repo i FineTuned a Pretrained ResNet18 model from PyTorch library

These notes and resources are compiled from the crash course Prompt Engineering for Vision Models offered by DeepLearning.AI.

Dataset for PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models

PoC Code for PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models

Diffusion Models crash course with Pytorch from DeepLearningAI

Testing the Moondream tiny vision model

An awesome list of "small but mighty" models and resources.

Vision-based swarms in the Presence of Occlusions