search

cvg / pixloc

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)
Apache License 2.0
735 stars 92 forks source link

Example of Training data #27

Open YanhaoZhang opened 2 years ago

YanhaoZhang commented 2 years ago

Hi Thanks a lot for releasing your project. This is a very intriguing work. I am wondering if you could provide a small-size example training dataset, just for understanding the code? The CMU dataset is too large, and very slow to be downloaded. Thanks a lot.

sarlinpe commented 2 years ago

You can train on a single slice of CMU, for example:

python -m pixloc.download --select CMU --CMU_slices 9 --training
python -m pixloc.pixlib.train pixloc_cmu_slice9 \
        --conf pixloc/pixlib/configs/train_pixloc_cmu.yaml \
        data.train_slices=[9] data.val_slices=[9]

This will use a subset of the training data for validation.

YanhaoZhang commented 2 years ago

@Skydes Thanks a lot for this suggestion. I will try this. :+1: