Pytorch Implement of the paper "Segmentation Based Deep-Learning Approach for Surface DefectDetection"

convert alg model

PyTorch wheels for aarch64 / ARM64, with vision, audio & text

pytorch实现bert做seq2seq任务

ElasticCTR 是基于 Kubernetes 的企业级推荐系统解决方案，该方案融合了百度业务场景下经过不断验证打磨的 CTR 模型、基于飞桨框架的大规模分布式训练、工业级稀疏

MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to mix symbolic and imperative programming to maximize efficiency and productivity. At its core, MXNet contains a dynamic dependency scheduler that automatica...

这一模型是用来研究具有多个输入，特别是具有多个输出的部门(称为决策单元，简称DMU)同时评估规模有效与技术有效的十分理想和卓有成效的方法

PaddleTS 是一个易用的深度时序建模的Python库，它基于飞桨深度学习框架PaddlePaddle，专注业界领先的深度模型，旨在为领域专家和行业用户提供可扩展的时序建模能力和便捷易用的用户体验。

PostgresML是PostgreSQL的机器学习扩展，能让你使用SQL查询对文本和表格数据进行训练和推理

TorchEI, 一个围绕DNN Reliability的研究和开发的高速工具包

基于深度学习的质谱预测

Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.

BMTrain 是一个高效的大模型训练工具包，可以用于训练数百亿参数的大模型。BMTrain 可以在分布式训练模型的同时，能够保持代码的简洁性。

torchplus is a utilities library that extends pytorch and torchvision

from https://github.com/tensorflow/models