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

ultralytics 8.0.168 save Tuner results every iteration (#4680)

Browse source
This commit is contained in:
Glenn Jocher 2023-08-31 23:40:42 +02:00 • committed by GitHub
parent 4b6147dd6f
commit 263bfd1e93
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 31 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ultralytics/utils/autobatch.py
View file

@ -29,7 +29,7 @@ def check_train_batch_size(model, imgsz=640, amp=True):
return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size
def autobatch(model, imgsz=640, fraction=0.67, batch_size=DEFAULT_CFG.batch):
def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
"""
Automatically estimate the best YOLO batch size to use a fraction of the available CUDA memory.