apoorva/greenhouse
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added param loss_ota for hyp.yaml, to disable OTA for faster training

Browse Source
This commit is contained in:
AlexeyAB84
2022-08-09 07:48:28 +03:00
parent 469a4d0e8d
commit 711a16ba57
5 changed files with 12 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
data/hyp.scratch.custom.yaml
+2 -1
View File
@@ -27,4 +27,5 @@ fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # image copy paste (probability)
paste_in: 0.0 # image copy paste (probability)
paste_in: 0.0 # image copy paste (probability), use 0 for faster training
loss_ota: 1 # use ComputeLossOTA, use 0 for faster training
data/hyp.scratch.p5.yaml
+2 -1
View File
@@ -27,4 +27,5 @@ fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.15 # image mixup (probability)
copy_paste: 0.0 # image copy paste (probability)
paste_in: 0.15 # image copy paste (probability)
paste_in: 0.15 # image copy paste (probability), use 0 for faster training
loss_ota: 1 # use ComputeLossOTA, use 0 for faster training
data/hyp.scratch.p6.yaml
+2 -1
View File
@@ -27,4 +27,5 @@ fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.15 # image mixup (probability)
copy_paste: 0.0 # image copy paste (probability)
paste_in: 0.15 # image copy paste (probability)
paste_in: 0.15 # image copy paste (probability), use 0 for faster training
loss_ota: 1 # use ComputeLossOTA, use 0 for faster training
data/hyp.scratch.tiny.yaml
+2 -1
View File
@@ -27,4 +27,5 @@ fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.05 # image mixup (probability)
copy_paste: 0.0 # image copy paste (probability)
paste_in: 0.05 # image copy paste (probability)
paste_in: 0.05 # image copy paste (probability), use 0 for faster training
loss_ota: 1 # use ComputeLossOTA, use 0 for faster training