Accidental use of PCN test data for validation?

AllenXiangX / SnowflakeNet

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

MIT License

142 stars 16 forks source link

Accidental use of PCN test data for validation? #16

Open lucasbrynte opened 1 year ago

lucasbrynte commented 1 year ago

Hi!

I just wanted to report what I think might be a mistake in using the PCN test data not only for testing, but also for validation. Shouldn't utils.data_loaders.DatasetSubset.TEST in the following rather be utils.data_loaders.DatasetSubset.VAL..? https://github.com/AllenXiangX/SnowflakeNet/blob/93e7151610765e7e2b41ace2d03c8750f0b6c80c/core/train_pcn.py#L36-L37

Regards, Lucas

AllenXiangX commented 1 year ago

Hi, Thank you for your interest in our work. To have a fair comparisn with previous work on the PCN benchmark, the model is trained on the training set and validated on the test set as most previous work does.