我的犀牛派A1上默认安装原生Ubuntu 24.04. 请问如何确认预置的 QNN (QCOM AI Engine Direct)的版本号？
这是我在默认Ubuntu下看到的目录结构，可以成功运行预置的yolov5 模型。这说明目前QNN的版本号是2.36吗? 谢谢
aidlux@aidlux:~/aidlite_demo/aidlite_qnn236/python$ python3 qnn_yolov5_multi.py 3
Aidlite library version : Aidlux_Aidlite_C4L_V2.3.2.248_65129e3_20260326
Aidlite python library version : Aidlux_Aidlite_P4L_V2.3.2.248_65129e3_20260326
[I20261103 09:43:03.135805 51421] [aidlite.cpp:284] [aidlite_core] model absolute path [/home/aidlux/aidlite_demo/aidlite_qnn236/data/qnn_yolov5_multi/cutoff_yolov5s_640_sigmoid_w8a8.qnn236.ctx.bin] .
[I20261103 09:43:03.135976 51421] [aidlite.cpp:644] [aidlite_core] model_header_magic model_header_amf_version[(]
[I20261103 09:43:03.136041 51421] [aidlite.cpp:784] [aidlite_core] real_name[/home/aidlux/aidlite_demo/aidlite_qnn236/data/qnn_yolov5_multi/cutoff_yolov5s_640_sigmoid_w8a8.qnn236.ctx]-suffix_framework[bin]
[I20261103 09:43:03.136066 51421] [aidlite.cpp:826] [aidlite_core] Trigger automatic inference for Config.
[I20261103 09:43:03.136166 51421] [aidlite.cpp:845] [aidlite_core] sysinfo flavor[enterprise]-platform[qc6490]
…
[I20261103 09:43:03.173840 51421] [aidlite.cpp:1366] [aidlite_core] Backend info: backend_name[aidlite_qnn236]-backend_version[V2.3.2.248]-backend_need_core_version[Aidlux_Aidlite_C4L_V2.3.2.X]-backend_build_id[cc54465c40d6d42a1af3c5ed5e62c22690818ecd].
[I20261103 09:43:03.173998 51421] [impl_qnn.cpp:315] [aidlite_qnn236] Enter InferenceLocalQNN::init() … …
[I20261103 09:43:03.174031 51421] [impl_qnn.cpp:334] [aidlite_qnn236] QNN Runtime_t type is DSP/HTP.
….
current [9] get_output_tensor cost time :0.0043637752532958984 ms
repeat [10] times , input[36.2701416015625]ms — invoke[54.30912971496582]ms — output[49.495697021484375]ms — sum[140.0749683380127]ms
检测到4个区域
1 [472, 232, 561, 519] 0.8130854 person
2 [211, 246, 282, 514] 0.81079763 person
3 [114, 230, 200, 545] 0.7994484 person
4 [86, 124, 557, 477] 0.7512346 bus
[I20261103 09:43:03.748179 51421] [impl_qnn.cpp:1281] [aidlite_qnn236] Enter InferenceLocalQNN::destory() … …
[I20261103 09:43:03.748236 51421] [impl_qnn.cpp:1286] [aidlite_qnn236] Starting destory iotensor for graphIdx: 0
/prj/qct/webtech_scratch20/mlg_user_admin/qaisw_source_repo/rel/qairt-2.36.0/release/snpe_src/avante-tools/prebuilt/dsp/hexagon-sdk-5.4.0/ipc/fastrpc/rpcmem/src/rpcmem_android.c:42:dummy call to rpcmem_deinit, rpcmem APIs will be used from libxdsprpc
The result image has been saved to : /home/aidlux/aidlite_demo/aidlite_qnn236/python/qnn_yolov5_multi.jpg
