Tianfang-Sun

Find Wrong Label in training set, segment-1994338527906508494_3438_100_3458_100_with_camera_labels.tfrecord, the 67th frame. In the 64th frame, the label for bicyclist is correct, see the fig below,  However, in the 67th frame,...

First of all, thanks for your hardworking to provide such a amazing dataset for us. I have successfully downloaded the dataset. However, I don't know where to find the labels...

Mismatch between accumulated point clouds and images

5

I'm trying to do cross-modal training between lidar and camera with this dataset. Therefore I project the labeled accumulated point clouds to the images and cut out the points that...

关于训练过程中loss突然变成nan，acc变成0的问题

9

您好，感谢您分享的代码，我在训练模型的过程中出现了loss突然变成nan，acc变成0的问题，我分别从头开始进行了两次训练，但是还是产生了一样的问题。 我的训练环境是： - Nvidia RTX 2080Ti cuda10.1+cudnn7.6.3 - python3.8.5+pytorch1.5.1 - 数据集是ILSVRC2015 - 由于显存只有11G，所以我在config里把batch_size改成了64 - 其他不变 请问您知道可能的原因是什么吗？您用的ImageNet-LT是由ILSVRC2015提取的吗？  

What do variable "id_step1", "nStep", "nBase" refer to in file balanced_replay.ipynb?

3

Hi @JoyHuYY1412 , thanks for sharing your codes here. You've proposed a novel paradigm for the LVIS task. I've met a problem when trying to run your code. Some variable...

Train PPT but got Loss = nan

3

Thanks for sharing the code! We follow the readme to prepare the enviorment and run the command: ``sh scripts/train.sh -g 4 -d nuscenes -c semseg-ppt-v1m1-0-nu-sk-wa-spunet -n semseg-ppt-v1m1-0-nu-sk-wa-spunet`` However, the loss...