本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Calculate signed distance fields for arbitrary meshes

1. Non-official implementation of Block-NeRF and Mega-NeRF in Pytorch. 2. Train your large-scale NeRF in the wild. 3. Weekly classified NeRF literature.

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

LibMTL: A PyTorch Library for Multi-Task Learning

C++ Primer 5 answers

Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

ONNX-TensorRT: TensorRT backend for ONNX

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

华为海思hi系列芯片使用的NNIE推理框架教程

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

bounding box prediction + intention prediction

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Fully Convolutional HarDNet for Segmentation in Pytorch

Dive into CPython internals, trying to illustrate every detail of CPython implementation

C++/Python Linux utility wrappers for NVIDIA Jetson - camera, codecs, CUDA, GStreamer, HID, OpenGL/XGL

A nnie quantization aware training tool on pytorch.

non-official PyTorch implementation of MobileNeXt from paper [Rethinking Bottleneck Structure for Efficient Mobile Network Design]

Siamese and triplet networks with online pair/triplet mining in PyTorch

Simple Online Realtime Tracking with a Deep Association Metric

SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)

pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

Efficient Large-Scale Point-Cloud Viewer based on OpenGL

船长关于机器学习、计算机视觉和工程技术的总结和分享

A PyTorch implementation of MobileNet V2 architecture and pretrained model.