Feature/tiered loss functions

appliedinnovation / fast-depth

ICRA 2019 "FastDepth: Fast Monocular Depth Estimation on Embedded Systems"

MIT License

0 stars 0 forks source link

Feature/tiered loss functions #16

Closed alexbarnett12 closed 3 years ago

alexbarnett12 commented 3 years ago

Implemented a Loss class that can combine any number of loss functions at different phases in the experiment. Currently, phases are based off the epoch.