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

Fix model re-fuse() in inference loops (#466)

Browse source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
This commit is contained in:
Glenn Jocher 2023-01-18 20:32:36 +01:00 • committed by GitHub
parent cc3c774bde
commit a86218b767
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 135 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ultralytics/yolo/engine/trainer.py
View file

@ -205,7 +205,7 @@ class BaseTrainer:
self.model = DDP(self.model, device_ids=[rank])
# Check imgsz
gs = max(int(self.model.stride.max() if hasattr(self.model, 'stride') else 32), 32) # grid size (max stride)
self.args.imgsz = check_imgsz(self.args.imgsz, stride=gs, floor=gs * 2)
self.args.imgsz = check_imgsz(self.args.imgsz, stride=gs, floor=gs)
# Batch size
if self.batch_size == -1:
if RANK == -1: # single-GPU only, estimate best batch size