About using my dataset to train semantic segmentation error in training

[mmiku1]

I would appreciate it if you could give me some advice and help. My dataset is made in the form of s3dis. @yanx27

[JayLuoShui]

hi，I want to know how to make my own dataset

[jiayaozi]

hello, i have the same error? but my error is "nan". have you solved this problem?

[sean880304]

@mmiku1 make sure you change those parameters regarding classes number with both files. line 24, 92 in train_semseg.py line 24, 30 in /data_utils/S3DISDataLoader.py

[XiaXinjie]

@mmiku1 make sure you change those parameters regarding classes number with both files. line 24, 92 in train_semseg.py line 24, 30 in /data_utils/S3DISDataLoader.py

Hello, If my data class is three. So, I need to change line 24, in the S3DISDataLoader.py, that is labelweights = np.zeros(13), I need to change the 13 to 3, right? And line 30 in theS3DISDataLoader.py, that is tmp, _ = np.histogram(labels, range(14)), where should I change?

Thank you very much.

[sean880304]

@mmiku1 make sure you change those parameters regarding classes number with both files. line 24, 92 in train_semseg.py line 24, 30 in /data_utils/S3DISDataLoader.py

Hello, If my data class is three. So, I need to change line 24, in the S3DISDataLoader.py, that is labelweights = np.zeros(13), I need to change the 13 to 3, right? And line 30 in theS3DISDataLoader.py, that is tmp, _ = np.histogram(labels, range(14)), where should I change?

Thank you very much.

I might need to look over the codes tomorrow, perhaps we can discuss this with each other thru WeChat?

[XiaXinjie]

@mmiku1 make sure you change those parameters regarding classes number with both files. line 24, 92 in train_semseg.py line 24, 30 in /data_utils/S3DISDataLoader.py

Hello, If my data class is three. So, I need to change line 24, in the S3DISDataLoader.py, that is labelweights = np.zeros(13), I need to change the 13 to 3, right? And line 30 in theS3DISDataLoader.py, that is tmp, _ = np.histogram(labels, range(14)), where should I change? Thank you very much.

I might need to look over the codes tomorrow, perhaps we can discuss this with each other thru WeChat?

QQ ok? My QQ number is 992128819 Thanks.

[sean880304]

@mmiku1 make sure you change those parameters regarding classes number with both files. line 24, 92 in train_semseg.py line 24, 30 in /data_utils/S3DISDataLoader.py

Hello, If my data class is three. So, I need to change line 24, in the S3DISDataLoader.py, that is labelweights = np.zeros(13), I need to change the 13 to 3, right? And line 30 in theS3DISDataLoader.py, that is tmp, _ = np.histogram(labels, range(14)), where should I change?

Thank you very much.

Hi, already send friend request. Yes, S3DISDataLoader.py line 24 change it to class number 3, and line 30 i think it's class number +1, so it becomes 4 in your case. Also im not 100% sure those are correct modifications since I haven't gotten a successful training result. May I ask how you process your dataset?

[sean880304]

@mmiku1 Hi, did you manage to train it successfully?

[foysalahmed10]

@sean880304 First, I would like to thank you for your time and support. I'm trying to train my own dataset. Can you tell me First how can i process my dataset for training. I already completed labeling the dataset. Now the dataset in .PCD format.

[gxyzka]

hello, i have the same error? but my error is "nan". have you solved this problem?

hi, I have the same training result, have you solved it?