search

zhongkaifu / Seq2SeqSharp

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.
Other
200 stars 39 forks source link

One unify seq2seq interop interface to backend - suggestion #20

Open GeorgeS2019 opened 3 years ago

GeorgeS2019 commented 3 years ago

It seems there is more recent initiative to speed up the completion of the Torch.Sharp binding interop to Torch C Api. There is now a seq2seq example implemented through Torch.Sharp.

If Seq2SeqSharp can adapt its backend to a more unifying interface that is compatible to the Torch.Sharp interop API to Torch C API, this will lead to a path with more complex Deep NLP seq2seq algorithm development.

zhongkaifu commented 3 years ago

Hi @GeorgeS2019 .

Thanks for your suggestion. Yes, this could be an area that anyone who is interested in can try. But currently, I mainly focus on other areas for Seq2SeqSharp, such as improving quality for machine translation and abstractive summarization tasks. I will keep this suggestion in my mind and may start to work on it in the future.

GeorgeS2019 commented 3 years ago

@zhongkaifu abstractive summarization tasks sounds exciting !