60 pointsby anantzoidover 9 years ago

4 comments

brudgersover 9 years ago

Github [from article]: <a href="https://github.com/baidu-research/warp-ctc" rel="nofollow">https://github.com/baidu-research/warp-ctc</a>

frikover 9 years ago

From the GitHub page: "This project contains our high performance CPU and CUDA versions of the CTC loss, along with bindings for <i>Torch</i>. The library provides a simple C interface, so that it is easy to integrate into deep learning frameworks."

NicoJuicyover 9 years ago

The hard part is not the technology, it's the large enough data sets. Perhaps finding good employees could also be a help

评论 #10922989 未加载

hartatorover 9 years ago

A tutorial: <a href="https://github.com/baidu-research/warp-ctc/blob/master/torch_binding/TUTORIAL.md" rel="nofollow">https://github.com/baidu-research/warp-ctc/blob/master/torch...</a>

Baidu’s AI Team Releases Key Deep-Learning Code

4 comments

Baidu’s AI Team Releases Key Deep-Learning Code

4 comments