JC Li

Check your gcc version. I met similar problem in ROS nodes building. Gcc 4.9 has linking problem, but gcc 5.4 works fine.

Also, a ROS publisher with Monocular + IMU is appreciated the same.

Keras provides customized metric argument while loading model. For example, https://github.com/keras-team/keras/issues/3911 IMHO, keras-vis could extract customized metrics from models being loaded, then call API appropriately.

It seems this is again python 2.7 python3 incompatibility issue. Tons of places to fix.

I got the demo notebook working with Python 3 in the branch I forked off: https://github.com/jinchenglee/tdb But I'm not the guy to do fully exaustive testing, so I just input...

Hi, I have a 16g+128g lichee Pi4a board. I've downloaded the LPI4A_FULL_20231214.zip image and tried to flash the board to use latest image. I've tried several times, it always hangs...

I just tried image LPI4A_BASIC_20231023.zip, it can be flashed without issue. However, image LPI4A_BASIC_20231214.zip hangs when writing 'boot' section. Seems image from Dec., 2023 cannot work on my board (I...

> Hi, I have a 16g+128g lichee Pi4a board. I've downloaded the LPI4A_FULL_20231214.zip image and tried to flash the board to use latest image. I've tried several times, it always...

Thank you for explanation. Since custom operator is an officially supported operator in ONNX spec, it seems a good practice to add some level of support in onnx-mlir? Of course,...

OK, I got to have tried RISC-V target with onnx-mlir. First, user should build the LLVM backend with RISC-V target besides the default X86 (the exact options might vary on...