HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Fix learning rate gap on resume (#9468)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: EunChan Kim <eunchan@hanyang.ac.kr>
Co-authored-by: Lakshantha Dissanayake <lakshanthad@yahoo.com>
Co-authored-by: RizwanMunawar <chr043416@gmail.com>
Co-authored-by: gs80140 <gs80140@users.noreply.github.com>
This commit is contained in:
Laughing 2024-04-02 17:55:11 +08:00 • committed by GitHub
parent e5f4f5c8b9
commit 1e547e60a0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 13 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ultralytics/utils/torch_utils.py
View file

@ -16,7 +16,7 @@ import torch.nn as nn
import torch.nn.functional as F
import torchvision
from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, __version__
from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, __version__
from ultralytics.utils.checks import PYTHON_VERSION, check_version
try:
@ -614,8 +614,9 @@ class EarlyStopping:
self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch
stop = delta >= self.patience # stop training if patience exceeded
if stop:
prefix = colorstr("EarlyStopping: ")
LOGGER.info(
f"Stopping training early as no improvement observed in last {self.patience} epochs. "
f"{prefix}Training stopped early as no improvement observed in last {self.patience} epochs. "
f"Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n"
f"To update EarlyStopping(patience={self.patience}) pass a new patience value, "
f"i.e. `patience=300` or use `patience=0` to disable EarlyStopping."