search

BIT-DA / SePiCo

[TPAMI 2023 ESI Highly Cited Paper] SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation https://arxiv.org/abs/2204.08808
https://arxiv.org/abs/2204.08808
Other
112 stars 7 forks source link

Could you point out where is the code for saving model parameters in the sepico repository? So that I can resume training from breakpoints? #24

Closed ZHE-SAPI closed 1 month ago

ZHE-SAPI commented 1 month ago

Where is the code for saving model parameters, so that it is convenient to resume training from breakpoints?

ZHE-SAPI commented 1 month ago

Oh, I got it. Just like this.

cfg.checkpoint_config = dict( by_epoch=False,
interval=1000,
max_keep_ckpts=5,
out_dir='path/to/checkpoints'
)