Glenn Jocher
43a616a955
PyTorch 1.6.0 compatability updates
4 лет назад
Glenn Jocher
fe094333e8
Update utils.py strip_optimizer() ( #509 )
Follow-on update that I missed adding into PR 509.
4 лет назад
Glenn Jocher
02445d176d
improved model.yaml source tracking
4 лет назад
Glenn Jocher
78c9420e09
--classes bug fix #387
4 лет назад
Glenn Jocher
094079bd26
update detect.py --class argument #387
4 лет назад
Glenn Jocher
e8cf24b6c8
Initial model ensemble capability #318
4 лет назад
Glenn Jocher
a40f615c6f
.half() bug fix
4 лет назад
Glenn Jocher
04bdbe4104
fuse update
4 лет назад
Glenn Jocher
2541f77946
update detect.py
4 лет назад
Glenn Jocher
1fdaa4987b
update detect.py
4 лет назад
Glenn Jocher
659ad748c8
update get_voc.sh
4 лет назад
Glenn Jocher
5323ad224d
export.py update
4 лет назад
Glenn Jocher
a62a1c2c67
export.py update
4 лет назад
Glenn Jocher
a9dc0c2c29
update check_img_size() for model strides
4 лет назад
Russ Ferriday
0d5065d3b9
Remove non-ascii that breaks pdb single-stepping
4 лет назад
Glenn Jocher
8c5b6220f5
Update detect.py
4 лет назад
Glenn Jocher
496ec33a33
Update detect.py
Added some recent updates that were missing, and updated the filename with an if else.
4 лет назад
Anish Hiranandani
68f63616b3
Fix after suggestion
4 лет назад
Glenn Jocher
b50fdf16af
model.names multi-GPU bug fix #94
4 лет назад
Glenn Jocher
227aa735dc
updates
4 лет назад
Glenn Jocher
6c1b87a42e
update google_utils import
4 лет назад
Glenn Jocher
bbd12c7cfe
detect.py fast bug fix
4 лет назад
Lornatang
2368603484
fix refrence bug
In torch==1.5, the import of the API has changed. Although it does not interrupt the operation of the program, it seems to me to be an implicit error and may throw an exception in later versions.
4 лет назад
Glenn Jocher
76ca367a01
FP16 to FP32 ckpt load
4 лет назад
Glenn Jocher
111994956e
switch default inference to FP16 on GPU
4 лет назад
Glenn Jocher
260b1729f0
FP16 inference update
4 лет назад
Glenn Jocher
099e6f5ebd
--img-size stride-multiple verification
4 лет назад
Glenn Jocher
ad71d2d513
update times to end-to-end latency (inference + NMS)
4 лет назад
Glenn Jocher
c14368d768
new CSP model release
4 лет назад
Glenn Jocher
c672bef10f
model fuse
4 лет назад
Glenn Jocher
dbdee3a4a3
multi-gpu test bug fix #15
4 лет назад
Glenn Jocher
ba9ab663a2
model.names for dataParallel
4 лет назад
Glenn Jocher
eb97b2e413
NMS fast mode
4 лет назад
Glenn Jocher
391492ee5b
updates
4 лет назад
Glenn Jocher
df7988d8d0
onnx_export.py
4 лет назад
Glenn Jocher
1e84a23f38
initial commit
4 лет назад