|
在3399pro上面运行roclx_face_recognition_demo, 人脸检测和特征点检测都没问题,加载人脸识别的模型会报错,信息如下
D RKNNAPI: ==============================================
D RKNNAPI: RKNN VERSION:
D RKNNAPI: API: 1.3.0 (c5654ea build: 2019-12-25 14:12:00)
D RKNNAPI: DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
D RKNNAPI: ==============================================
D RKNNAPI: ==============================================
D RKNNAPI: RKNN VERSION:
D RKNNAPI: API: 1.3.0 (c5654ea build: 2019-12-25 14:12:00)
D RKNNAPI: DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
D RKNNAPI: ==============================================
E RKNNAPI: rknn_init, msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
E RKNNAPI: ==============================================
E RKNNAPI: RKNN VERSION:
E RKNNAPI: API: 1.3.0 (c5654ea build: 2019-12-25 14:12:00)
E RKNNAPI: DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
E RKNNAPI: ==============================================
rockx load_model(74): rknn_init fail! ret=-6
rockx init(72): init module(3) error -1
0 box=(80 63 168 195) score=0.999992
get_max_face 0
Segmentation fault (core dumped)
可见前两个init都成功了,就recog的报了错
C++ 和 python的demo都是这样,是不是我face recognition 的data文件有损坏?
|
|