这些优秀的组织正在使用:

Updated 16 hours ago

Updated 17 hours ago Text

开源脉冲神经网络深度学习框架

Updated 20 hours ago Python

天元(MegEngine)是旷视自主研发的开源深度学习框架,于2020年3月正式在 OpenI 启智社区开源,天元能够帮助开发者高效的完成深度学习算法的设计、训练、部署,有效提升AI研发工作效率。

Updated 1 day ago C++

A flexible and extensible framework for brain modeling

Updated 1 day ago Python

TensorLayer3.0一款兼容多深度学习框架后端的深度学习库, 目前可以用TensorFlow、MindSpore、PaddlePaddle作为后端计算引擎。

Updated 1 day ago Python

面向多计算场景的一站式融合计算平台

Updated 1 day ago CSS

面向多计算场景的一站式融合计算平台

Updated 1 day ago CSS

面向多计算场景的一站式融合计算平台

Updated 1 day ago CSS

本项目是群体化方法与技术的开源实现案例,在基于Gitea的基础上,进一步支持社交化的协同开发、协同学习、协同研究等群体创新实践服务,特别是针对新一代人工智能技术特点,重点支持项目管理、git代码管理、大数据集存储管理与智能计算平台接入。

Updated 1 day ago Go

TOWARDS UNBIASED COVID-19 LESION LOCALISATION AND SEGMENTATION VIA WEAKLY SUPERVISED LEARNING Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.

Updated 2 days ago

TOWARDS UNBIASED COVID-19 LESION LOCALISATION AND SEGMENTATION VIA WEAKLY SUPERVISED LEARNING Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.

Updated 2 days ago

HRNet作为骨架网络的方案在语义分割、目标检测、人体姿态估计等领域均取得了较好的应用。它主要的创新特色如下:将高分辨率之间的连接由串联改为并联;在整个网络结构中都保持了高分辨率的表征;在高低分辨率中引入了交互来提高模型性能。

Updated 2 days ago Python

octopus-doc

Updated 2 days ago SVG

ELMo MindSpore version

Updated 3 days ago Python

PanGu-Alpha 模型在 GPU 上推理和训练-测试

Updated 4 days ago Python

TensorLayer3.0一款兼容多深度学习框架后端的深度学习库, 目前可以用TensorFlow、MindSpore、PaddlePaddle作为后端计算引擎。

Updated 5 days ago Python