KPConv-PyTorch

KPConv-PyTorch copied to clipboard

FileNotFoundError: [Errno 2] No such file or directory: 'F:\\KPConv\\Data\\SemanticKitti\\sequences\\00\\poses.txt'

sanfenzhongmeichifanle

Should calibration be re-computed for inference on new data?

5

Hi Thomas Hugues, many thanks for this pytorch version of KPConv. Applying a trained model on new data with different point density using `test_model.py` recomputes the calibration if the `batch_limits.pkl`...

floriandeboissieu

Hi I'm trying to use your repository to train on a custom dataset Do you have any recommendation for memory? RAM and VRAM?

francescobodria

Did you use the calibrations data?

1

################## # Load calibration ################## # Init variables self.calibrations = [] self.times = [] self.poses = [] self.all_inds = None self.class_proportions = None self.class_frames = [] self.val_confs = [] #...

magical1998

Hi! I'm training a model using the S3DIS dataset, and I have some questions regarding input dimensions and features. 1. What does in_features_dim represent? This value is set to 5,...

gitKincses

Hi Thomas, I just made some slight revisions for this code, if I find something can be improved futher, I will submit it again. Thank you for your work!

GeoSur

KPConv Bias Toward Dominant Classes — How to Break Semantic Collapse?

7

**Hi everyone,** I'm currently running my KPConv pipeline for the first times using a small sample of real training data. The dataset comes from a Mobile Mapping System (MMS) and...

TokyoWarfare

-1 flag when padding

1

I've been trying to run KPConv into a custom pipeline and ran into a critical issue that I think deserves attention. The repo uses -1 as a padding flag for...

TokyoWarfare

Validation def missing! :D

2

Hello, I'm trying to run my own MMS dataset. After a lot of pain I've managed to get out of the pit just to find a funny missing piece in...

TokyoWarfare

Hi, I'm new to this network, I downloaded the pretrained weight and S3DIS dataset, ran test_models.py as the instructions said, but it took too long to prepare the dataset, and...

ChenxiWang09