mace icon indicating copy to clipboard operation
mace copied to clipboard

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Results 65 mace issues
Sort by recently updated
recently updated
newest added

1.我们在集成mace的时候发现dlclose后crash,但是无法定位到是哪个线程导致的,请创建线程的时候加上线程名便于debug; 2.mace某些线程无法正常退出 ![image](https://user-images.githubusercontent.com/37567308/179882276-83964298-04d4-41bb-b631-eb9cb33ab545.png)

我看目前mace提供的APU库文件,只有mt67xx的只有6779(P90)和6785(G90)的库文件,想问下6771(P60)支持APU吗?支持的话也是需要使用apu-frontend和apu-platform的方式吗?

建议更新一下demo相关的工具,比如bazel有点老的

将onnx模型转mace models时,一个conv op转换失败,报错如下: Traceback (most recent call last): File "tools/converter.py", line 1334, in flags.func(flags) File "tools/converter.py", line 926, in convert_func convert.convert(configs, MODEL_CODEGEN_DIR, flags.enable_micro) File "tools/python/convert.py", line 89, in convert net_def_with_Data...

There is a small bug here, unlike other cmake build scripts, that causes the system to get particularly stuck.

从高通官方博客[blog](https://developer.qualcomm.com/blog/accelerate-your-models-our-opencl-ml-sdk)上得知,从adreno 660开始,高通官方增加了cl_qcom_ml_ops扩展,速度比目前开源实现的opencl 代码都要快一些;我从小米11的手机上adb pull /system/vendor/lib64/libOpenCL.so,本地nm -D看过,确实有clQueryMLInterfaceVersionsQCOM的符号表,但是调用以后会报CL_OUT_OF_HOST_MEMORY的错误,请问是小米还没有更新adreno的驱动导致的吗?

大佬你好, 在MACE文档中看到下面这句 Well, the good news is that starting in the SM8150 family(some devices with old firmware may still not work), signature-free dynamic module offload is enabled on cDSP. So,...

onnx模型里面有LOOP和IF算子,支持这种结构吗?