mirror
/
MODNet
mirror of https://github.com/ZHKKKe/MODNet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update the comments

pull/63/head
Zhanghan Ke 2021-01-28 18:40:25 +08:00 committed by GitHub
parent 9106a62265
commit c432f592e7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/trainer.py
View File

@ -93,9 +93,12 @@ def supervised_training_iter(
modnet (torch.nn.Module): instance of MODNet modnet (torch.nn.Module): instance of MODNet
optimizer (torch.optim.Optimizer): optimizer for supervised training optimizer (torch.optim.Optimizer): optimizer for supervised training
image (torch.autograd.Variable): input RGB image image (torch.autograd.Variable): input RGB image
its pixel values should be normalized
trimap (torch.autograd.Variable): trimap used to calculate the losses trimap (torch.autograd.Variable): trimap used to calculate the losses
NOTE: foreground=1, background=0, unknown=0.5 its pixel values can be 0, 0.5, or 1
(foreground=1, background=0, unknown=0.5)
gt_matte (torch.autograd.Variable): ground truth alpha matte gt_matte (torch.autograd.Variable): ground truth alpha matte
its pixel values are between [0, 1]
semantic_scale (float): scale of the semantic loss semantic_scale (float): scale of the semantic loss
NOTE: please adjust according to your dataset NOTE: please adjust according to your dataset
detail_scale (float): scale of the detail loss detail_scale (float): scale of the detail loss
@ -184,6 +187,7 @@ def soc_adaptation_iter(
backup_modnet (torch.nn.Module): backup of the trained MODNet backup_modnet (torch.nn.Module): backup of the trained MODNet
optimizer (torch.optim.Optimizer): optimizer for self-supervised SOC optimizer (torch.optim.Optimizer): optimizer for self-supervised SOC
image (torch.autograd.Variable): input RGB image image (torch.autograd.Variable): input RGB image
its pixel values should be normalized
soc_semantic_scale (float): scale of the SOC semantic loss soc_semantic_scale (float): scale of the SOC semantic loss
NOTE: please adjust according to your dataset NOTE: please adjust according to your dataset
soc_detail_scale (float): scale of the SOC detail loss soc_detail_scale (float): scale of the SOC detail loss