zjc
/
yolov5
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

train with multi-gpu half test bug fix #99

This commit is contained in:
Glenn Jocher 2020-06-16 16:28:25 -07:00
parent d1e5716610
commit 2daa412575
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
test.py
View File

@ -46,7 +46,8 @@ def test(data,
else: # called by train.py else: # called by train.py
training = True training = True
device = next(model.parameters()).device # get model device device = next(model.parameters()).device # get model device
half = device.type != 'cpu' and torch.cuda.device_count() == 1 # half precision only supported on single-GPU # half disabled https://github.com/ultralytics/yolov5/issues/99
half = False # device.type != 'cpu' and torch.cuda.device_count() == 1
if half: if half:
model.half() # to FP16 model.half() # to FP16