commit | bbe20bb347da90909c2ae9d345c2efb3481a5abd | [log] [tgz] |
---|---|---|
author | Hua Jiang <huaj@xilinx.com> | Wed Feb 26 15:52:28 2020 -0800 |
committer | GitHub <noreply@github.com> | Wed Feb 26 15:52:28 2020 -0800 |
tree | 7fa622264a624337ac6333003c60b7d888177aba | |
parent | 436850fe7ec6576b28b7148cf9b6548fd6ca3f7d [diff] |
[VTA] YoloV3 Support (#4887) * [VTA] YoloV3 Support Issue: YoloV3 use some operator and logic that not get good support by existing vta logic, like nn.pad, upsample, and 255 output channel. Solution: add related logic to let darknet YoloV3 can running on VTA * Fix small(0, or 1 heigh/width) detect frame issue. * add yolov3-tiny turtorial * add os import * address review comments. * rename tutorial file with a short name. * rename deploy_vision_on_vta.py into deploy_classification.py. * address review comment, fix plint eror in deploy_detection.py
VTA (versatile tensor accelerator) is an open-source deep learning accelerator complemented with an end-to-end TVM-based compiler stack.
The key features of VTA include:
Learn more about VTA here.