R2D dataset issue about sne-roadseg HOT 8 CLOSED

Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.

from sne-roadseg.

Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.

Thank you very much!!! Sorry for the stupid question ☹.

from sne-roadseg.

Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.
Hi, @hlwang1124 . I just tried to train by the kitti dataset with resnet 18. And it had an error after an epoch.

(epoch: 1, iters: 290, time: 0.115, data: 0.068) segmentation: 0.463
End of epoch 1 / 1000 Time Taken: 119 sec
learning rate = 0.0010000
Traceback (most recent call last):
File "train.py", line 119, in
avg_valid_loss = torch.mean(torch.stack(valid_loss_iter))
RuntimeError: expected a non-empty list of Tensors

Could you help to fix it? Thanks!!!

from sne-roadseg.

Hi, @SimonSongg . Our R2D dataset is collected in the Carla simulation environment. Please refer to this link for the data format of depth maps and semantic segmentation maps.

I comment lines

119: avg_valid_loss = torch.mean(torch.stack(valid_loss_iter))
123: writer.add_scalar('valid/loss', avg_valid_loss, epoch)

in train.py and I can train without any error.

from sne-roadseg.

It seems that you did not split a validation set.

from sne-roadseg.

It seems that you did not split a validation set.

sorry for the stupid mistake!!!!!!!! I forgot it. Thank you for your patience.

from sne-roadseg.

It's OK. Happy to see that everything works now:)

from sne-roadseg.

Excuse me,I haved referred to https://carla.readthedocs.io/en/stable/cameras_and_sensors/ for the data format of depth maps and semantic segmentation maps,but I still don't how can I convert the depth images and the labels.Could you please tell me the
specific conversion operation？Thank you very much!!!!

from sne-roadseg.