光源殿下
光源殿下
yes，just change paras in argparser
I'have the same issue with you... AndI found this import sys import numpy as np A = sys.path.insert(0, "..") from distutils.core import setup from distutils.extension import Extension from Cython.Build import...
> but the successive code is likely to be wrong
metoo，我也是最后一步遇到了这个情况，而且我确认了torch.version.cuda和cuda都是11.3版本的
没解决...虽然这么说挺不好的但是我放弃了，建议使用mmrotate，更好部署一些....
可以使用x2paddle先保存成paddle的pd_model模型在cpu上运行 这步我之前验证了（用python），没有问题的。 paddle lite的opt工具将pdmodel转换为nb模型 这个就是用paddle官方C++代码，加载成功，调用就会崩溃，是在rk3588+麒麟系统上做的。 关于精度，我知道enable_fp16 设置为 ON，但是直接转化有个参数可以用INT8的精度，不知道这个是不是可以
yeah, I've deal with this successfully, but still wondering why did this happens? Seems like caused by an abusing of wrong pth?
after sevral times repeating, it works now, but the second motor of the follower always hold to the max value 78.134766: >>> follower_pos = robot.follower_arms["main"].read("Present_Position") >>> print(follower_pos) [ -2.4609375 **78.134766**...
and red light on the second motor is blinking......
Sevral times tries have been made, including restarting even restoring by dynamixel wizard 2, but failed. things are strange when after configuring, in the rest position: >>> leader_pos = robot.leader_arms["main"].read("Present_Position")...