Commit 95d68a32 authored by LDOUBLEV's avatar LDOUBLEV
Browse files

fix inference

parent f822b08b
...@@ -49,9 +49,9 @@ Jeston端基础训练预测功能测试的主程序为`test_train_inference_pyth ...@@ -49,9 +49,9 @@ Jeston端基础训练预测功能测试的主程序为`test_train_inference_pyth
```shell ```shell
bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer'
# 用法1: # 用法1:
bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' bash test_tipc/test_inference_jeston.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer'
# 用法2: 指定GPU卡预测,第三个传入参数为GPU卡号 # 用法2: 指定GPU卡预测,第三个传入参数为GPU卡号
bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' '1' bash test_tipc/test_inference_jeston.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' '1'
``` ```
运行相应指令后,在`test_tipc/output`文件夹下自动会保存运行日志。如`lite_train_lite_infer`模式下,会运行训练+inference的链条,因此,在`test_tipc/output`文件夹有以下文件: 运行相应指令后,在`test_tipc/output`文件夹下自动会保存运行日志。如`lite_train_lite_infer`模式下,会运行训练+inference的链条,因此,在`test_tipc/output`文件夹有以下文件:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment