search

wayveai / fiery

PyTorch code for the paper "FIERY: Future Instance Segmentation in Bird's-Eye view from Surround Monocular Cameras"
https://wayve.ai/blog/fiery-future-instance-prediction-birds-eye-view
MIT License
549 stars 87 forks source link

data loading #19

Closed sjbling closed 2 years ago

sjbling commented 2 years ago

why the lenth of self.indices is 10? Is this means only train 10 samples data?

anthonyhu commented 2 years ago

That's when debugging using the "mini" NuScenes dataset. If you train the model on the full dataset as specified in the config https://github.com/wayveai/fiery/blob/master/fiery/configs/baseline.yml the dataset size is much bigger.