Glenn Jocher
|
a63e1c9b3c
|
study update
|
5 years ago |
|
Glenn Jocher
|
db898131f9
|
study update
|
5 years ago |
|
Glenn Jocher
|
6c1b87a42e
|
update google_utils import
|
5 years ago |
|
Glenn Jocher
|
1f1917ef56
|
remove fast, add merge
|
5 years ago |
|
Glenn Jocher
|
2daa412575
|
train with multi-gpu half test bug fix #99
|
5 years ago |
|
Glenn Jocher
|
d1e5716610
|
train with multi-gpu half test bug fix #99
|
5 years ago |
|
Glenn Jocher
|
72d06147b2
|
Multi-GPU disabled in test.py
|
5 years ago |
|
Glenn Jocher
|
7c6fd4d670
|
--verbose bug fix #84
|
5 years ago |
|
Glenn Jocher
|
db2c3acd3a
|
updated testing settings, rebalanced towards FP16 latency
|
5 years ago |
|
Glenn Jocher
|
0b514daced
|
FP16 test loss bug fix
|
5 years ago |
|
Glenn Jocher
|
a1748a8d6e
|
test during training default to FP16
|
5 years ago |
|
Glenn Jocher
|
76ca367a01
|
FP16 to FP32 ckpt load
|
5 years ago |
|
Glenn Jocher
|
c5966abba8
|
glob search bug fix #77
|
5 years ago |
|
Glenn Jocher
|
e7c24e04ac
|
half() fix #66
|
5 years ago |
|
Glenn Jocher
|
111994956e
|
switch default inference to FP16 on GPU
|
5 years ago |
|
Glenn Jocher
|
157aff2854
|
FP16 inference fix
|
5 years ago |
|
Glenn Jocher
|
260b1729f0
|
FP16 inference update
|
5 years ago |
|
Glenn Jocher
|
099e6f5ebd
|
--img-size stride-multiple verification
|
5 years ago |
|
Glenn Jocher
|
d187459dd4
|
study changes
|
5 years ago |
|
Glenn Jocher
|
546f973562
|
model fuse
|
5 years ago |
|
Glenn Jocher
|
208493d959
|
updates
|
5 years ago |
|
Glenn Jocher
|
dbdee3a4a3
|
multi-gpu test bug fix #15
|
5 years ago |
|
Glenn Jocher
|
ba9ab663a2
|
model.names for dataParallel
|
5 years ago |
|
Glenn Jocher
|
2a0aff685a
|
dataset padding mode
|
5 years ago |
|
Glenn Jocher
|
eb97b2e413
|
NMS fast mode
|
5 years ago |
|
Glenn Jocher
|
ee8988b8a2
|
datasets.py self.batch_shapes fix
|
5 years ago |
|
Glenn Jocher
|
7960c4c5d8
|
updates
|
5 years ago |
|
Glenn Jocher
|
ce36905358
|
updates
|
5 years ago |
|
Glenn Jocher
|
1e84a23f38
|
initial commit
|
5 years ago |
