Paddle-Lite object-detect android替换模型后运行崩溃

deikduxw  于 2021-12-01  发布在  Java
关注(0)|答案(4)|浏览(286)

02-24 15:53:14.680 23521 23553 F libc : Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0x0 in tid 23553 (Predictor Worke), pid 23521 (bject_detection)
02-24 15:53:14.744 23561 23561 I crash_dump64: obtaining output fd from tombstoned, type: kDebuggerdTombstone
02-24 15:53:14.745 985 985 I /system/bin/tombstoned: received crash request for pid 23553
02-24 15:53:14.746 23561 23561 I crash_dump64: performing dump of process 23521 (target tid = 23553)
02-24 15:53:14.751 23561 23561 F DEBUG :************************************************
02-24 15:53:14.751 23561 23561 F DEBUG : Build fingerprint: 'Xiaomi/chiron/chiron:9/PKQ1.190118.001/9.9.3:user/release-keys'
02-24 15:53:14.751 23561 23561 F DEBUG : Revision: '0'
02-24 15:53:14.751 23561 23561 F DEBUG : ABI: 'arm64'
02-24 15:53:14.751 23561 23561 F DEBUG : pid: 23521, tid: 23553, name: Predictor Worke >>> com.baidu.paddle.lite.demo.object_detection <<<
02-24 15:53:14.751 23561 23561 F DEBUG : signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0x0
02-24 15:53:14.751 23561 23561 F DEBUG : Cause: null pointer dereference
02-24 15:53:14.751 23561 23561 F DEBUG : x0 0000000000000006 x1 0000000000000000 x2 0000000000000001 x3 0000000000000015
02-24 15:53:14.751 23561 23561 F DEBUG : x4 000000000000004e x5 0000007286dffbd8 x6 0000005a00000074 x7 000000c60000009c
02-24 15:53:14.751 23561 23561 F DEBUG : x8 fec3bbff8149f50f x9 0000000000000017 x10 000000000000001f x11 00000000ffffffff
02-24 15:53:14.751 23561 23561 F DEBUG : x12 000000c60000009c x13 0000014600000175 x14 0000000000000000 x15 0000007286dfc8b0
02-24 15:53:14.751 23561 23561 F DEBUG : x16 00000072753b1820 x17 0000007312e6eef0 x18 0000007286dfcd60 x19 0000007286d01840
02-24 15:53:14.751 23561 23561 F DEBUG : x20 000000727576c4c0 x21 000000727576c4d8 x22 000000727576c4f0 x23 0000007286cba840
02-24 15:53:14.751 23561 23561 F DEBUG : x24 0000000012dc12c0 x25 0000000000000003 x26 0000000000000002 x27 000000000000012c
02-24 15:53:14.751 23561 23561 F DEBUG : x28 000000727576c5e0 x29 000000727576c5e0
02-24 15:53:14.751 23561 23561 F DEBUG : sp 000000727576c490 lr 0000007275197714 pc 00000072751977d8
02-24 15:53:14.752 23561 23561 F DEBUG :
02-24 15:53:14.752 23561 23561 F DEBUG : backtrace:
02-24 15:53:14.752 23561 23561 F DEBUG : #0 pc 00000000000ec7d8 /data/app/com.baidu.paddle.lite.demo.object_detection-7rl7R4ad6gg3UagtxvlRkw==/lib/arm64/libpaddle_lite_jni.so
02-24 15:53:15.161 23561 23561 E MIUINDBG: miui_native_debug_process_O

gstyhher

gstyhher1#

您好,我们已经收到了您的问题,会安排技术人员尽快解答您的问题,请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时,您也可以通过查看官网文档常见问题历史Issue来寻求解答。祝您生活愉快~

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the APIFAQ and Github Issue to get the answer.Have a nice day!

v7pvogib

v7pvogib2#

建议在 https://github.com/PaddlePaddle/Paddle-Lite/releases 选择制定版本的opt工具生成nb模型,然后用对应的lite库和头文件替换demo中的文件。

tyg4sfes

tyg4sfes3#

模型是yolov3_mobilenet_v1,官方demo是2.7,我也是用2.7opt生成nb的,看到文章说yolov3有bug。自己编译换成2.8的还是一样的错误,同样的图片,我换了一个模型ssdlite_mobilenet_v3,训练完成后,2.7opt生成nb就可以使用

mlmc2os5

mlmc2os54#

请问 您有解决该问题吗。

相关问题