Glenn Jocher
ab7ff9dd4c
Revert "cv2.imread(img, -1) for IMREAD_UNCHANGED" ( #1778 )
2021-05-31 10:40:13 +02:00
Glenn Jocher
4d0c2e6eee
YOLOv5 v5.0 release compatibility update for YOLOv3
2021-05-30 18:55:56 +02:00
Glenn Jocher
8eb4cde090
YOLOv5 v5.0 release compatibility update for YOLOv3 ( #1737 )
...
* YOLOv5 v5.0 release compatibility update
* Update README
* Update README
* Conv act LeakyReLU(0.1)
* update plots_study()
* update speeds
2021-04-12 18:00:47 +02:00
Glenn Jocher
166a4d590f
v9.1 release ( #1658 )
2021-01-12 23:05:32 -08:00
Glenn Jocher
fed9451454
f.read().strip() ( #1577 )
2020-11-29 12:01:42 +01:00
Glenn Jocher
76807fae71
YOLOv5 Forward Compatibility Update ( #1569 )
...
* YOLOv5 forward compatibility update
* add data dir
* ci test yolov3
* update build_targets()
* update build_targets()
* update build_targets()
* update yolov3-spp.yaml
* add yolov3-tiny.yaml
* add yolov3-tiny.yaml
* Update yolov3-tiny.yaml
* thop bug fix
* Detection() device bug fix
* Use torchvision.ops.nms()
* Remove redundant download mirror
* CI tests with yolov3-tiny
* Update README.md
* Synch train and test iou_thresh
* update requirements.txt
* Cat apriori autolabels
* Confusion matrix
* Autosplit
* Autosplit
* Update README.md
* AP no plot
* Update caching
* Update caching
* Caching bug fix
* --image-weights bug fix
* datasets bug fix
* mosaic plots bug fix
* plot_study
* boxes.max()
* boxes.max()
* boxes.max()
* boxes.max()
* boxes.max()
* boxes.max()
* update
* Update README
* Update README
* Update README.md
* Update README.md
* results png
* Update README
* Targets scaling bug fix
* update plot_study
* update plot_study
* update plot_study
* update plot_study
* Targets scaling bug fix
* Finish Readme.md
* Finish Readme.md
* Finish Readme.md
* Update README.md
* Creado con Colaboratory
2020-11-26 20:24:00 +01:00
Shiwei Song
cf652962fd
fix padding for rectangular inference ( #1524 )
...
Co-authored-by: swsong <swsong@stratosphere.mobi>
2020-10-19 12:17:14 +02:00
Glenn Jocher
e80cc2b80e
Update datasets.py
2020-07-20 10:34:06 -07:00
Glenn Jocher
f61fa7de2b
Update datasets.py
2020-07-20 10:33:49 -07:00
Glenn Jocher
183e3833d2
update datasets.py
2020-06-20 09:58:48 -07:00
Glenn Jocher
cf7a4d31d3
bug fix in local to global path replacement
2020-05-28 20:50:02 -07:00
Glenn Jocher
e99ff3aad0
local path robustness
2020-05-28 14:01:38 -07:00
Glenn Jocher
16ea613628
caching introspection update
2020-05-22 16:06:21 -07:00
Glenn Jocher
4879fd22e9
caching introspection update
2020-05-22 16:03:08 -07:00
Glenn Jocher
2cc2b2cf0d
label *.npy saving for faster caching
2020-05-20 21:39:18 -07:00
Glenn Jocher
3ddaf3b63c
label *.npy saving for faster caching
2020-05-20 21:13:41 -07:00
Glenn Jocher
bbd82bb94d
updates
2020-05-17 14:30:12 -07:00
Josh Veitch-Michaelis
992d8af242
faster hsv augmentation ( #1110 )
...
As per https://github.com/ultralytics/yolov3/issues/1096
2020-04-28 12:59:44 -07:00
Glenn Jocher
15f1343dfc
uncached label removal
2020-04-28 11:07:26 -07:00
Glenn Jocher
693c06b26c
bug fix issues/1067
2020-04-18 12:07:44 -07:00
Glenn Jocher
2cf23c4aee
add MixConv2d() layer
2020-04-10 18:58:34 -07:00
Glenn Jocher
4bbfda5cde
hist equalization
2020-04-10 17:29:57 -07:00
Glenn Jocher
9bc3a551d9
histogram equalization added to augmentation
2020-04-10 17:24:49 -07:00
Glenn Jocher
aa8b1098dd
adapt mosaic to img channel count
2020-04-10 16:28:59 -07:00
Glenn Jocher
6736d7d125
swap cv2.INTER_AREA for cv2.INTER_LINEAR
2020-04-10 12:47:07 -07:00
Glenn Jocher
f54d28ba63
improve assert no labels found
2020-04-08 09:57:59 -07:00
Glenn Jocher
6c5ecaf805
remove label loading during training
2020-04-07 16:57:22 -07:00
Glenn Jocher
26fc4fb018
dataloader default color to imagenet mean 114
2020-04-05 18:02:41 -07:00
Glenn Jocher
4da5c6c114
rect padding to 64, mAP increase 42.7 to 42.9
2020-04-05 16:06:27 -07:00
Glenn Jocher
585064f300
updates
2020-03-10 13:33:14 -07:00
Glenn Jocher
dce753ead4
updates
2020-03-02 14:30:01 -08:00
Glenn Jocher
bc741f30e8
updates
2020-02-22 18:18:38 -08:00
Yonghye Kwon
145ea67a2e
modify h range clip range in hsv augmentation ( #825 )
...
* h range clip range edit in hsv augmentation
h range is [0., 179,]
* Update datasets.py
reduced indexing operations and used inplace clip for hsv. Two clips are used unfortunately (double clip of axis 0), but the overall effect should be improved speed.
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-02-07 09:14:55 -08:00
Glenn Jocher
dca80f6f98
updates
2020-02-06 16:13:10 -08:00
Glenn Jocher
bab855507a
updates
2020-01-17 18:05:28 -08:00
Glenn Jocher
dec2c7d9a6
updates
2020-01-17 17:52:28 -08:00
Glenn Jocher
c0cde1edf0
updates
2020-01-16 13:25:18 -08:00
Glenn Jocher
77034467f6
updates
2020-01-11 20:13:29 -08:00
Glenn Jocher
4b56a370e6
updates
2020-01-11 13:13:57 -08:00
Glenn Jocher
b7a25e60ce
updates
2020-01-10 13:41:47 -08:00
Glenn Jocher
3505b57421
updates
2020-01-10 11:55:54 -08:00
Glenn Jocher
6e52f985fe
updates
2020-01-10 11:45:51 -08:00
Glenn Jocher
0219eb094e
updates
2020-01-09 21:05:26 -08:00
Glenn Jocher
1aedf27886
updates
2020-01-05 06:11:00 -08:00
Glenn Jocher
d859957c66
updates
2019-12-27 12:34:29 -08:00
Glenn Jocher
b58f41ef53
updates
2019-12-27 09:29:09 -08:00
Glenn Jocher
03b5408e70
updates
2019-12-15 12:15:56 -08:00
Glenn Jocher
0465500b37
updates
2019-12-13 18:52:08 -08:00
Glenn Jocher
074a9250d8
updates
2019-12-13 12:27:52 -08:00
Glenn Jocher
2300cb964a
updates
2019-12-08 19:58:42 -08:00