Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, x86, x64, ARM), multimodal model for text and images and so on.
A couple of important upgrades are included in this package, such as
The demo package is also updated and more new applications are included.
Full Changelog: https://github.com/zhongkaifu/Seq2SeqSharp/compare/RELEASE_2_4...RELEASE_2_4_1
Some new features added and performance improvement. In release package, add a new multi-languages translation model for English to CJK (Chinese, Japanese and Korean).
Add new application tools for multi-tasks. Retrained some models using larger vocabularies