search

WHU-USI3DV / WHU-Railway3D

(IEEE TITS 2024) WHU-Railway3D: A Diverse Dataset and Benchmark for Railway Point Cloud Semantic Segmentation
123 stars 2 forks source link

AttributeError: ‘Railway3DDataset’ object has no attribute ‘validation_split’ #8

Open pping0412 opened 3 weeks ago

pping0412 commented 3 weeks ago

Hello Professor, I haav some problems with training and visualization: Q1:AttributeError: ‘Railway3DDataset’ object has no attribute ‘validation_split’,subsequently I changed this line of code to: if val_loader.dataset.val_file_name not in val_loader.dataset.all_file_name: .

1731288434000

Q2:Error when running visualisation code:I ndexError: list index out of range 1731401447488

boqiuphd commented 1 week ago

Hello Professor, I haav some problems with training and visualization: Q1:AttributeError: ‘Railway3DDataset’ object has no attribute ‘validation_split’,subsequently I changed this line of code to: if val_loader.dataset.val_file_name not in val_loader.dataset.all_file_name. Q2:Error when running visualisation code:I ndexError: list index out of range.

Thank you for your interest in our work!

A1: Your training phase is fine, but the error occurs during the validation phase. Please check if the value of self.val_paths in Railway3D.py is correct, and verify whether the validation data has been correctly loaded into the DataLoader.

A2: I have not encountered a similar error before, and with the limited information you provided, I cannot pinpoint the exact cause of the issue. You might consider asking ChatGPT or Copilot for assistance.