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

New dataset fraction=1.0 argument (#2860)

Browse source
This commit is contained in:
Glenn Jocher 2023-05-28 02:13:46 +02:00 • committed by GitHub
parent 61fa5efe6d
commit 0bdd4ad379
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 16 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ultralytics/yolo/cfg/default.yaml
View file

@ -30,6 +30,7 @@ cos_lr: False # use cosine learning rate scheduler
close_mosaic: 0 # (int) disable mosaic augmentation for final epochs
resume: False # resume training from last checkpoint
amp: True # Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
fraction: 1.0 # dataset fraction to train on (default is 1.0, all images in train set)
# Segmentation
overlap_mask: True # masks should overlap during training (segment train only)
mask_ratio: 4 # mask downsample ratio (segment train only)