Jiongyi Meng

Hi, I probably know how to fix this. As shown below, in the place of the cls_loss function in the original loss_utils.py file, the definitions of cls_pc_raw and cls_aug_raw are...

> Hi, To address this issue, I forked this repo and add a script for docker visualization. You could check: [https://github.com/BayRanger/SensorsCalibration](url) And the usage has been added to README >...

> Hi! How did you get full 3D map? Just run `roslaunch lidar_imu_init xxx.launch` ?? Yes.

> > what > > It seems strange. If a point cloud frame is splitted into 10 parts based on timestamps, each frame would only have a FoV of 36°,...

需要根据场景大小选择filter size，室内和室外差别很大的。 还有就是拆分lidar子帧的时候需要适当调大拆分率，需要多试几次。

3DM-GX5-25 is good in my experience.

@YoYo000 我的微信号是mz0120090558，有些问题想和大家讨论，能拉我进群吗，谢谢！

> 感谢你的回应。 当我在训练MVSFormer（Twins-based）的时候能够正常进入loss迭代界面，但是在训练MVSFormer（frozen DINO-based）的时候，出现了报错： File "/home/aszitao/anaconda3/envs/mvsformer/lib/python3.7/site-packages/torch/cuda/amp/grad_scaler.py", line 137, in _check_scale_growth_tracker assert self._scale is not None, "Attempted {} but _scale is None. ".format(funcname) + fix AssertionError: Attempted step but _scale is...

> > > 感谢你的回应。 当我在训练MVSFormer（Twins-based）的时候能够正常进入loss迭代界面，但是在训练MVSFormer（frozen DINO-based）的时候，出现了报错： File "/home/aszitao/anaconda3/envs/mvsformer/lib/python3.7/site-packages/torch/cuda/amp/grad_scaler.py", line 137, in _check_scale_growth_tracker assert self._scale is not None, "Attempted {} but _scale is None. ".format(funcname) + fix AssertionError: Attempted step but...

如果我用自己的相机拍摄的照片放到模型里的话，是不是相机的内参和外参必须提前计算出来？如果外参是必须的话，那么使用什么方法或者什么工具能比较简单地计算呢？