README.md 722 字节
Newer Older
W
wangjiawei04 已提交
1 2 3 4 5 6 7 8 9 10 11 12
# Faster RCNN HRNet model on Paddle Serving

([简体中文](./README_CN.md)|English)

### Get The Faster RCNN HRNet Model
```
wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/faster_rcnn_hrnetv2p_w18_1x.tar
```

### Start the service
```
tar xf faster_rcnn_hrnetv2p_w18_1x.tar
T
TeslaZhao 已提交
13
python3 -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
W
wangjiawei04 已提交
14 15
```

H
HexToString 已提交
16 17
This model support TensorRT, if you want a faster inference, please use `--use_trt`. But you need to do some extra work.
Please reference to https://github.com/PaddlePaddle/Paddle-Inference-Demo/blob/master/c%2B%2B/paddle-trt/trt_dynamic_shape_test.cc#L40 
W
wangjiawei04 已提交
18 19 20 21


### Prediction
```
T
TeslaZhao 已提交
22
python3 test_client.py 000000570688.jpg
W
wangjiawei04 已提交
23
```