基于Yolo V3的动漫头像检测模型，仅需200张标注数据即可在多种番剧、线描、背面等场景下实现较高检出率。开源代码和模型权重，支持开箱即用。
Articles in the Computing category
Catastrophic Failure
DigitalOcean server incidents and migration to Azure—site layout may be temporarily affected during the transition.
Tagged as : EnglishGigapixel Panoramas
Creating gigapixel panoramas with Leica SL and vintage R lenses: from Seattle skyline to macro photography of watches and dollar bills, with tips for successful stitching.
能理解聊天记录的微信机器人(三)
基于Caffe的斗图机器人：用深度学习提取表情特征，在数据库中找最近邻实现自动回复，效果意外地好但也暴露了ImageNet预训练模型在二次元表情上的局限。
能理解聊天记录的微信机器人(二)
微信机器人功能升级：群标签云统计、个人发言分析、活跃度可视化，并接入ElasticSearch和Kibana实现实时监控，算法从TF升级到TF-IDF。