ValueError: Input must be 1- or 2-d.

Hi!
I just do it 'python test_pretrain_SemanticKITTI.py' with KITTI Dataset, but the training is wrong!
I put two files 01 、04 under the data file.
What should i do?
thanks!

(pytorch) ziudarkin@ziudarkin-ubuntu:~/PolarSeg$ python test_pretrain_SemanticKITTI.py 
test_pretrain_SemanticKITTI.py
Namespace(data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='pretrained_weight/SemKITTI_PolarSeg.pt', test_batch_size=1, test_output_path='out/SemKITTI_test')
********************************************************************************
Test network performance on validation split
********************************************************************************
0it [00:00, ?it/s]Traceback (most recent call last):
  File "test_pretrain_SemanticKITTI.py", line 185, in <module>
    main(args)
  File "test_pretrain_SemanticKITTI.py", line 122, in main
    iou = per_class_iu(sum(hist_list))
  File "test_pretrain_SemanticKITTI.py", line 26, in per_class_iu
    return np.diag(hist) / (hist.sum(1) + hist.sum(0) - np.diag(hist))
  File "<__array_function__ internals>", line 6, in diag
  File "/home/ziudarkin/anaconda3/envs/pytorch/lib/python3.7/site-packages/numpy/lib/twodim_base.py", line 303, in diag
    raise ValueError("Input must be 1- or 2-d.")
ValueError: Input must be 1- or 2-d.
0it [00:00, ?it/s]

@edwardzhou130 can you help me .

Looks like it's because the valid split data is missing:

PolarSeg/semantic-kitti.yaml

Lines 187 to 211 in 3531f15

You can move one file like 04 to the valid split or just simply skip the whole validation part.

Looks like it's because the valid split data is missing:

PolarSeg/semantic-kitti.yaml

Lines 187 to 211 in 3531f15

train:

- 0

- 1

- 2

- 3

- 4

- 5

- 6

- 7

- 9

- 10

valid:

- 8

test:

- 11

- 12

- 13

- 14

- 15

- 16

- 17

- 18

- 19

- 20

- 21

You can move one file like 04 to the valid split or just simply skip the whole validation part.

hi, @edwardzhou130 ,Thank you for your answer. I solved the previous problem in a muddle, but I encountered a new problem, as follows

(pytorch) ZiuDarkin@dl-station303:~/PolarSeg$ python train_SemanticKITTI.py
train_SemanticKITTI.py
Namespace(check_iter=4000, data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='./SemKITTI_PolarSeg.pt', train_batch_size=2, val_batch_size=2)
  0%|                                      | 0/136 [00:00<?, ?it/s]Traceback (most recent call last):
  File "train_SemanticKITTI.py", line 197, in <module>
    main(args)
  File "train_SemanticKITTI.py", line 129, in main
    iou = per_class_iu(sum(hist_list))
  File "train_SemanticKITTI.py", line 27, in per_class_iu
    return np.diag(hist) / (hist.sum(1) + hist.sum(0) - np.diag(hist))
AttributeError: 'int' object has no attribute 'sum'
  0%|                                      | 0/136 [00:01<?, ?it/s]

Does this error mean that there is a problem with the calculation method of hist matrix？
best wish

I think I know why, but thank you very much
best wish

	train:
	- 0
	- 1
	- 2
	- 3
	- 4
	- 5
	- 6
	- 7
	- 9
	- 10
	valid:
	- 8
	test:
	- 11
	- 12
	- 13
	- 14
	- 15
	- 16
	- 17
	- 18
	- 19
	- 20
	- 21