yujunjun/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-12-25 14:08:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix inference

Browse Source
This commit is contained in:
LDOUBLEV 2021-11-15 11:15:35 +08:00
parent f822b08bd0
commit 95d68a32bf
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
test_tipc/docs/jeston_test_train_inference_python.md
View File

@ -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
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:
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
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：