Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

在 Loss 配置中增加 out_channel， 方便自定义数据训练 #9439

Closed
wants to merge 3 commits into from
Closed

在 Loss 配置中增加 out_channel， 方便自定义数据训练 #9439

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4303f36
在 Loss 配置中增加 out_channel， 方便自定义数据训练
Mar 15, 2023
fe4e394
Add the out_channel default value
Mar 17, 2023
bfde4e2
Merge branch 'PaddlePaddle:release/2.6' into release/2.6
LittleGhosts Mar 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions configs/rec/rec_d28_can.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,7 @@ Architecture:

Loss:
name: CANLoss
out_channel: 111

PostProcess:
name: CANLabelDecode
Expand Down
4 changes: 2 additions & 2 deletions ppocr/losses/rec_can_loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,11 +28,11 @@ class CANLoss(nn.Layer):
counting_loss: counting loss of every symbol
'''

def __init__(self):
def __init__(self, out_channel=111):
super(CANLoss, self).__init__()

self.use_label_mask = False
self.out_channel = 111
self.out_channel = out_channel
self.cross = nn.CrossEntropyLoss(
reduction='none') if self.use_label_mask else nn.CrossEntropyLoss()
self.counting_loss = nn.SmoothL1Loss(reduction='mean')
Expand Down