Effortless data labeling with AI support from Segment Anything and other awesome models.
-
Updated
Jun 21, 2024 - Python
Effortless data labeling with AI support from Segment Anything and other awesome models.
🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.
Here are all my code files of Advanced AI/ML architectures built from scratch using Pytorch.
Implementation of popular deep learning networks with TensorRT network definition API
A toolbox of vision models and algorithms based on MindSpore
Commercial iOS fall detection app. Connects to a Polar H10 device for triaxial acceleromter and ECG signals. These signals are passed to a trained ResNet152 model using Tensorflow background processes for live inference.
Implement an intelligent diagnostic system capable of accurately classifying cardiac activity. By analyzing ECG images or electronic readings, the system aims to detect various abnormalities, including distinguishing normal vs. abnormal heartbeats, identifying myocardial infarction (MI) and its history, and assessing the impact of COVID-19.
The goal of this project is to employ deep learning models and advanced techniques to identify abnormalities by analyzing images of the skin tissues.
带你从零实现一个高性能的深度学习推理库,支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
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.
PaddlePaddle End-to-End Development Toolkit(飞桨低代码开发工具)
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
EZAutoMate: Your AI-powered Car Sales Advisor
Created an AI to match food images with recipes, beating benchmarks with ResNet and BERT. Achieved top-10 recall of 82.49% and a median rank of 1 using triplet loss networks.
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Add a description, image, and links to the resnet topic page so that developers can more easily learn about it.
To associate your repository with the resnet topic, visit your repo's landing page and select "manage topics."