search

charlesq34 / pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Other
4.64k stars 1.44k forks source link

semantic segmentation data split #190

Open thirdlastletter opened 4 years ago

thirdlastletter commented 4 years ago

Hi, I am confused about the semantic segmentation files. I have a 3fold cross validation set. I can use train.py with both my train and test data. What do I need batch_interference for then? Just for the visualization/prediction? So I need to use both train.py and batch_intereference.py on one set of train/test files, and repeat this for the other 2 versions? Thank you.

Thank you for the help!

jean-noelp commented 4 years ago

Hi,

Currently, I am studying this project, and i think i understood some points.

Normally, "test data" must be differents to "train data". "Test data" are used for each epoch to evaluate learning evolution.

The inference step should be used when the model is ready (with learning ended), and consists to the last step : the use of your frozen model, which is faster than learning use.