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
560 stars 85 forks source link

May I know where is the checkpoint getting saved? #39

Closed pranavi77 closed 2 years ago

pranavi77 commented 2 years ago

I dont see anywhere that the checkpoint is getting saved and while resuming the training, I am getting an error that "size mismatch for model.temporal_model.model.1.aggregation.0.conv.weight"

anthonyhu commented 2 years ago

Hi,

The weights are saved in fiery/tensorboard_logs by default. You can change this folder by modifying the LOG_DIR field in https://github.com/wayveai/fiery/blob/master/fiery/config.py

Have you changed the size of the temporal model while resuming traning?

pranavi77 commented 2 years ago

got it thank you so much. somehow my default folder is not being created.