Rocky Song
Rocky Song
你好,看到这个模型很受启发,我想把这个模型迁移成识别少量交通控制标志,用于智能车的竞赛中。使用的器件是i.MX RT1062,它的CPU是600MHz的arm Cortex-M7,大约有等效的2个int16 MAdd每周期,利用率约30%多点。也可以考虑更高性能的i.MX RT1176,1GHz Cortex-M7。 但麻烦的是这种IoT用途的芯片不能运行Linux和ncnn,但是能使用GLOW模型编译器编译onnx模型为目标文件,或者把Keras格式的模型翻译成命令列表后并使用一个解释引擎去执行。 基于这种条件,想请问有什么推荐的思路去移植吗?
CMSIS-NN NN functions heavily rely on some 4-byte accessor functions, such as: __STATIC_FORCEINLINE q31_t arm_nn_read_q7x4_ia(const q7_t **in_q7) { q31_t val; memcpy(&val, *in_q7, 4); *in_q7 += 4; return (val); } However,...
### Bug description Unresolved external **__std_init_once_link_alternate_names_and_abort@0,** which is referred by public: __thiscall std::_Init_once_completer::~_Init_once_completer(void) (??1_Init_once_completer@std@@QAE@XZ) ### Steps to reproduce Just follow "BUILDING.md" without changing any options, selecting WIN32, CMake version was...
If I modified -W and -H to non-512x512, such as (384,384), (1024, 1024), (256, 256), the lip motion is damaged in different degrees. The most severe setting is under 1024x1024,...