apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[benchmark] optimize benchmark bin usage (#1868)

Browse Source 
* [benchmark] add disable_mkldnn option for paddle infer backend to support 3D model

* [benchmark] optimize benchmark bin usage

* [benchmark] optimize benchmark bin usage
This commit is contained in:
DefTruth
2023-04-25 11:43:59 +08:00
committed by GitHub
parent 37794d5f45
commit 430fc424ac
2 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/cpp/README.md
+8 -1
View File
@@ -165,8 +165,15 @@ FastDeploy除了提供包含模型前后处理在内的benchmark_xxx外，也提
| model_file | Optional, set specific model file, eg, model.pdmodel, model.onnx, default "UNKNOWN" |
| params_file | Optional, set specific params file, eg, model.pdiparams, default "" |
| model_format | Optional, set specific model format, eg, PADDLE/ONNX/RKNN/TORCHSCRIPT/SOPHGO, default "PADDLE" |
| disable_mkldnn | Whether to disable mkldnn for paddle backend, default false. |
### 5.1 benchmark工具使用示例
### 5.1 benchmark工具使用示例
- 用法说明
```bash
./benchmark --helpshort
benchmark: ./benchmark -[info|diff|check|dump|mem] -model xxx -config_path xxx -[shapes|dtypes|names|tensors] -[model_file|params_file|model_format]
...
```
- 单输入示例：
```bash
./benchmark --model ResNet50_vd_infer --config_path config/config.x86.ov.fp32.txt --shapes 1,3,224,224 --names inputs --dtypes FP32