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

main code

Browse Source 
fix gain for train_aux
This commit is contained in:
Kin-Yiu, Wong 2022-07-14 16:49:38 +08:00 committed by GitHub
parent 4cebf4000a
commit ef4dde425b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
utils/loss.py
View File

@ -1115,7 +1115,7 @@ class ComputeLossBinOTA:
# Build targets for compute_loss(), input targets(image,class,x,y,w,h) # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
na, nt = self.na, targets.shape[0] # number of anchors, targets na, nt = self.na, targets.shape[0] # number of anchors, targets
indices, anch = [], [] indices, anch = [], []
gain = torch.ones(7, device=targets.device) # normalized to gridspace gain gain = torch.ones(7, device=targets.device).long() # normalized to gridspace gain
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
@ -1561,7 +1561,7 @@ class ComputeLossAuxOTA:
# Build targets for compute_loss(), input targets(image,class,x,y,w,h) # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
na, nt = self.na, targets.shape[0] # number of anchors, targets na, nt = self.na, targets.shape[0] # number of anchors, targets
indices, anch = [], [] indices, anch = [], []
gain = torch.ones(7, device=targets.device) # normalized to gridspace gain gain = torch.ones(7, device=targets.device).long() # normalized to gridspace gain
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
@ -1614,7 +1614,7 @@ class ComputeLossAuxOTA:
# Build targets for compute_loss(), input targets(image,class,x,y,w,h) # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
na, nt = self.na, targets.shape[0] # number of anchors, targets na, nt = self.na, targets.shape[0] # number of anchors, targets
indices, anch = [], [] indices, anch = [], []
gain = torch.ones(7, device=targets.device) # normalized to gridspace gain gain = torch.ones(7, device=targets.device).long() # normalized to gridspace gain
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices