Problems with semseg about dgcnn.pytorch HOT 9 CLOSED

File "D:\dgcnn.pytorch-master\data.py", line 149, in load_data_semseg
test_area_name = "Area_" + test_area
TypeError: can only concatenate str (not "NoneType") to str

I have set test_area = ‘1’ but when printing it output 'none' in the terminal

from dgcnn.pytorch.

I think the path "D:\dgcnn.pytorchV2\data/stanford_indoor3d\Stanford3dDataset_v1.2_Aligned_Version\Area_1_conferenceRoom_1.txt" should be "D:\dgcnn.pytorchV2\data\stanford_indoor3d\Stanford3dDataset_v1.2_Aligned_Version\Area_1_conferenceRoom_1.txt"

from dgcnn.pytorch.

Thanks a lot! I used '//' to replace all the'', and finally generated .npy in the folder. These files are not in the correct directory, I need to move them manually. The previous error was due to the gen_indoor3d_h5.py not running correctly.
What's more, pred = seg_pred.max(dim=2)[1](in main_semseg.py, line 111) leads to the following error：
IndexError: Dimension out of range (expected to be in range of [-2, 1], but got 2)
I have noticed in the main_cls.py, the parameter is dim=1. Could you please explain the difference?

from dgcnn.pytorch.

By the way, after the terminal outputs 'Let's use 1 GPUs! Use SGD', there is no new output for about two hours. Is this a normal phenomenon?

from dgcnn.pytorch.

Please use the batch size --batch_size larger than 1.

from dgcnn.pytorch.

Could you give me some information about the training time on the task of semseg with 1 GPUs and batch size is 32, for the full dataset?

from dgcnn.pytorch.

Because I use 4 GPUs, I can't provide the training time for 1 GPU.

from dgcnn.pytorch.

Could you tell me your training time for reference?Thanks in advance

from dgcnn.pytorch.

I remember the time is less than one day.

from dgcnn.pytorch.