Which Khadas SBC do you use?
VIM3
Which system do you use? Android, Ubuntu, OOWOW or others?
Ubuntu
Which version of system do you use? Khadas official images, self built images, or others?
Please describe your issue below:
I tried to run NPU demo like below.
NPU SDK Usage [Khadas Docs]
NPU Prebuilt Demo Usage [Khadas Docs]
I got the result of NPU demo following.
khadas@Khadas:~/Project/aml_npu_demo_binaries/detect_demo_picture$ ./detect_demo_x11 0 1080p.bmp
W Detect_api:[det_set_log_level:19]Set log level=1
W Detect_api:[det_set_log_level:21]output_format not support Imperfect, default to DET_LOG_TERMINAL
W Detect_api:[det_set_log_level:26]Not exist VSI_NN_LOG_LEVEL, Setenv set_vsi_log_error_level
det_set_log_config Debug
E [vnn_CreateYoloface:168]Open file nn_data/yolo_face_88.nb failed.
E [model_create:60]CHECK PTR 60
E Detect_api:[det_set_model:225]Model_create fail, file_path=nn_data, dev_type=1
det_set_model fail. ret=-4
So I saw to need yolo_face_88.nb file in nn_data directory, I found that in repository from url below.
After I put yolo_face_88.nb file in nn_data directory, I ran again with making script like run.sh. I reviewed demo code from github repository(GitHub - khadas/aml_npu_app)
run.sh
#!/bin/sh
export VSI_NN_LOG_LEVEL=0
./detect_demo_x11 -m 0 -p /home/khadas/Project/aml_npu_demo_binaries/detect_demo_picture/1080p.bmp
khadas@Khadas:~/Project/aml_npu_demo_binaries/detect_demo_picture$ ./run.sh
W Detect_api:[det_set_log_level:19]Set log level=1
W Detect_api:[det_set_log_level:21]output_format not support Imperfect, default to DET_LOG_TERMINAL
det_set_log_config Debug
E Detect_api:[det_set_model:225]Model_create fail, file_path=nn_data, dev_type=1
det_set_model fail. ret=-4
I don’t know why happened model_create fail. Finally, I attach my directory tree.
khadas@Khadas:~/Project/aml_npu_demo_binaries/detect_demo_picture$ tree
.
├── 1080p.bmp
├── detect_demo_fb
├── detect_demo_x11
├── graph.json
├── INSTALL
├── lib
│ ├── libnn_detect.so
│ ├── libnn_facenet.so
│ ├── libnn_yoloface.so
│ ├── libnn_yolo_tiny.so
│ ├── libnn_yolo_v2.so
│ ├── libnn_yolo_v3.so
│ └── libnn_yolo_v4.so
├── nn_data
│ ├── inception_v3.nb
│ ├── mobilenet_tf.nb
│ ├── yolo_face_88.nb
│ └── yolo_face_88.nb_new
├── README.md
├── run.sh
├── test.py
└── UNINSTALL
Could I know what I was wrong? Or what should I do some more?
Post a console log of your issue below:
khadas@Khadas:~/Project/aml_npu_demo_binaries/detect_demo_picture$ ./detect_demo_x11 0 1080p.bmp
W Detect_api:[det_set_log_level:19]Set log level=1
W Detect_api:[det_set_log_level:21]output_format not support Imperfect, default to DET_LOG_TERMINAL
W Detect_api:[det_set_log_level:26]Not exist VSI_NN_LOG_LEVEL, Setenv set_vsi_log_error_level
det_set_log_config Debug
E [vnn_CreateYoloface:168]Open file nn_data/yolo_face_88.nb failed.
E [model_create:60]CHECK PTR 60
E Detect_api:[det_set_model:225]Model_create fail, file_path=nn_data, dev_type=1
det_set_model fail. ret=-4
khadas@Khadas:~/Project/aml_npu_demo_binaries/detect_demo_picture$ ./run.sh
W Detect_api:[det_set_log_level:19]Set log level=1
W Detect_api:[det_set_log_level:21]output_format not support Imperfect, default to DET_LOG_TERMINAL
det_set_log_config Debug
E Detect_api:[det_set_model:225]Model_create fail, file_path=nn_data, dev_type=1
det_set_model fail. ret=-4