Detectron2: production environment

Created on 28 Nov 2019  路  3Comments  路  Source: facebookresearch/detectron2

how to deployment model to production environment,when can we see detectron2go?

Most helpful comment

detectron2go will support pytorch->onnx->caffe2's efficient inference on server/mobile CPUs. We don't have any GPU inference pipeline.
We hope to release it soon but no concrete timeline.

All 3 comments

I second, also will detectron2go support pytorch->onnx->tensorRT pipeline?

detectron2go will support pytorch->onnx->caffe2's efficient inference on server/mobile CPUs. We don't have any GPU inference pipeline.
We hope to release it soon but no concrete timeline.

@ppwwyyxx got it, thanks!

Was this page helpful?
0 / 5 - 0 ratings