onionysy

Results 9 issues of onionysy

我在自己的数据中运行程序出现节点错误,但并没有报出具体的错误。 ![图片](https://user-images.githubusercontent.com/55376216/163197903-b84d17c1-48f2-47cf-835c-71935ce0948a.png) 所以我在不同地方添加输出消息,定位到出错的位置(lidar_camera_calib/loadCalibConfig)。 ![图片](https://user-images.githubusercontent.com/55376216/163198270-72fcf795-267e-41ea-9d6c-42d4409c532e.png) 运行消息显示,在fSettings初始化时就出现了错误。我们之前通过相类似的读取方式,是可以读取标定文件的。我也在网上查找相关问题,并没找到有效的答案。 不知道您是否能给出建设性的意见?感谢您的回复。

Thank you very much for your excellent work. I used your network to train and test on my own data set, but found that the effect was not very good....

In the course of training, we encountered this problem `/home/buaa/anaconda3/envs/vit/bin/python3.6 /snap/pycharm-community/302/plugins/python-ce/helpers/pydev/pydevd.py --multiprocess --qt-support=auto --client 127.0.0.1 --port 45947 --file /home/buaa/songyue/lawin-master/tools/train.py Connected to pydev debugger (build 222.4345.23) fatal: not a git repository...

![2022-05-17 16-16-34屏幕截图](https://user-images.githubusercontent.com/55376216/168763874-506c8c10-1784-4289-8a9f-ed723c9aed06.png) When we build a map on our own dataset, there are a large number of kdtree errors, as shown in the figure. Although this does not affect the...

We want to debug using a single graphics card with pycharm, instead of using distributed training. But we ran into the following problems: ------------------------------------------------------------ fatal: not a git repository (or...

We tried to generate the results of the model according to "docs/run.md", but we could not find the results saved. Do you have any suggestions?

How to use pytorch2onnx.py?

我们在openlane公开数据集上进行训练,但是训练到一半出现了cuda error的问题。我们怀疑这是数据集车道线类别超出了21类的限制?但是在用openlane.py处理数据集的时候,我们看到有对于超出的类别进行了修改 ``` if lane_results['category'] >= 21: lane_results['category'] = 20 ``` 我们目前已经不知道是那里出了问题,您有什么建议吗?报错信息如下: `2023-07-28 00:20:42,672 - mmseg - INFO - Exp name: anchor3dlane_iter.py 2023-07-28 00:20:42,673 - mmseg - INFO - Iter...

We trained the openlane dataset with iter, but the effect is not ideal, may I ask where we have not configured well?