R. He
R. He
I tried again a few days later and it worked. I connected to Jetson NX at first and it was failed again. But I retried and to my surprise, it...
Same as me. Have you ever found the reasons as well as the solutions?
还有一个警告信息我没有附上，不知道是否相关： ``` E:\anaconda3\lib\site-packages\pandas\core\computation\expressions.py:20: UserWarning: Pandas requires version '2.7.3' or newer of 'numexpr' (version '2.7.1' currently installed). from pandas.core.computation.check import NUMEXPR_INSTALLED ```
In `kimera_semantics_euroc.launch`, the depth image is no need. How about trying to just use stereo images?
Add a transformation between {robot_name}/map to world may help you, like this https://github.com/MIT-SPARK/Kimera-Multi/issues/3#issuecomment-1793603701
参考这篇[文章](https://blog.csdn.net/qq_45701501/article/details/142554430)
[Bug]: 输入文件的路径 (..\..\..\Transformer-For-Geochemical-Anomaly-Detection-main) 存在，但位置非法。请将文件上传后再执行该任务。
看了下代码，要么上传，要么放在gpt_academic目录下的gpt_log或tests或build里。虽然保证了安全，但终究不大方便。要是不上传到该目录下就把调用 `validate_path_safety` 的那行先注释了吧。会在报错的地方显示是哪个函数哪一行调用了 `validate_path_safety`
btw，存档的对话历史是使用 `3.74` 版本的对话，现在载入用的是最新的 `3.76` 版本
感觉是一次性发送到llm，导致token数过大？因为调用了其他API，反映token数超过限制