Open hanxiao opened 4 years ago
Hi, I'm the leader of Mindspore ModelZoo. Thanks for your constructive suggestions. Regarding NLP, I suggest using the encoder in Transformer model or using BERT model directly. Regarding CV, you can use VGG or Resnet50 as the encoder. The pretrained model and the related instructions will be released soon. If you have any more specific requirements, please let us know and keep in touch. Thank you.
this issue is solved in these two PRs
I will write a blog post as a wrap-up.
Task Description
I'd like to build a demo using Mindspore as the DL infra in Jina. http://github.com/jina-ai/jina
I already create a mirror issue at here https://github.com/jina-ai/jina/issues/431
Task Goal
Implement two encoders, one in NLP, one in CV with Mindspore and add them to the executor family of Jina.
Would be great if anyone can provide some pretrained models, this will greatly speedup the dev process and onboarding for new developers.
Sub Task