CoreML custom layer (GPU-accelerated) and converter for torchvision.ops.deform_conv2d

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Use your camera to control the mouse from a distance

Minerva project includes the minerva package that aids in the fitting and testing of neural network models. Includes pre and post-processing of land cover data. Designed for use with torchgeo datasets.

Torch extension for calculating the Intersection over Union (IoU) for quadrilaterals, supports CPU and CUDA tensors. Handles both 1-to-1 and M-to-N matches, returning an IoU matrix with M rows and N columns.

Pytorch_to_Tensorflow

The road sign recognition system of the Russian Federation, which uses an already prepared model for object detection and image segmentation in real time to improve road safety

💡💡💡awesome compute vision app in gradio

View model summaries in PyTorch!

Vision Model - Modular: A repository showcasing modular code for training and structuring computer vision models, facilitating easy experimentation and deployment.

HealthBotML is an intelligent healthcare companion powered by machine learning (ML) and artificial intelligence (AI). With HealthBotML, you can seamlessly check your Body Mass Index (BMI) and engage in informative conversations about various diseases.

A neural network framework for researchers studying acoustic communication

💎A high level pipeline for face landmarks detection, it supports training, evaluating, exporting, inference(Python/C++) and 100+ data augmentations, can easily install via pip.

A project is a second part of Introduction to Machine Learning course. Here the problem is image recognition on CIFAR10 dataset using 2 different approaches: simple model and transfer learning using pretrained model.

AI based security system!

视觉相关的编程语法、计算框架以及视觉库使用

🔶 Visualization utilities for PyTorch.

💤 PyTorch bootcamp.

This project is an approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. The developed model is able to recognize 38 different types of plant diseases out of of 14 different plants with the ability to distinguish plant leaves from their surroundings.

Разработка сверточной нейронной сети для классификации изображений