2022-06-07 18:05:51 +08:00
|
|
|
# PPLNN Support
|
2021-10-09 14:10:42 +08:00
|
|
|
|
2022-12-13 14:21:24 +08:00
|
|
|
MMDeploy supports ppl.nn v0.9.1 and later. This tutorial is based on Linux systems like Ubuntu-18.04.
|
2021-11-09 11:43:38 +08:00
|
|
|
|
2022-06-07 18:05:51 +08:00
|
|
|
## Installation
|
2021-11-09 11:43:38 +08:00
|
|
|
|
|
|
|
|
1. Please install [pyppl](https://github.com/openppl-public/ppl.nn) following [install-guide](https://github.com/openppl-public/ppl.nn/blob/master/docs/en/building-from-source.md).
|
|
|
|
|
|
2022-06-07 18:05:51 +08:00
|
|
|
2. Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
|
2021-11-09 11:43:38 +08:00
|
|
|
|
2022-06-07 18:05:51 +08:00
|
|
|
## Usage
|
2021-11-09 11:43:38 +08:00
|
|
|
|
|
|
|
|
Example:
|
2022-06-17 09:19:10 +08:00
|
|
|
|
2021-11-09 11:43:38 +08:00
|
|
|
```bash
|
|
|
|
|
python tools/deploy.py \
|
2021-12-14 15:04:39 +08:00
|
|
|
configs/mmdet/detection/detection_pplnn_dynamic-800x1344.py \
|
2021-11-09 11:43:38 +08:00
|
|
|
/mmdetection_dir/mmdetection/configs/retinanet/retinanet_r50_fpn_1x_coco.py \
|
|
|
|
|
/tmp/snapshots/retinanet_r50_fpn_1x_coco_20200130-c2398f9e.pth \
|
|
|
|
|
tests/data/tiger.jpeg \
|
|
|
|
|
--work-dir ../deploy_result \
|
|
|
|
|
--device cuda \
|
2022-06-07 18:05:51 +08:00
|
|
|
--log-level INFO
|
2021-11-09 11:43:38 +08:00
|
|
|
```
|
