Skip to content

sacred config for faster rcnn #1358

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.

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

Merged
merged 25 commits into from
Jul 8, 2020
Merged
Changes from 1 commit
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
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
Prev Previous commit
Merge remote-tracking branch 'upstream/estimator' into pr-rcnn
  • Loading branch information
Jerryzcn committed Jul 8, 2020
commit b2cd33c739909057e2f8f329fa72b4b93fa524a6
6 changes: 4 additions & 2 deletions gluoncv/pipelines/estimators/rcnn/faster_rcnn.py
Original file line number Diff line number Diff line change
Expand Up @@ -281,9 +281,11 @@ def __init__(self, config, logger=None, reporter=None):
' Default setting is for MS-COCO.')
self._logger.info(self._cfg)
self.rpn_cls_loss = gluon.loss.SigmoidBinaryCrossEntropyLoss(from_sigmoid=False)
self.rpn_box_loss = gluon.loss.HuberLoss(rho=self._cfg.train_hp.rpn_smoothl1_rho) # == smoothl1
self.rpn_box_loss = gluon.loss.HuberLoss(
rho=self._cfg.train_hp.rpn_smoothl1_rho) # == smoothl1
self.rcnn_cls_loss = gluon.loss.SoftmaxCrossEntropyLoss()
self.rcnn_box_loss = gluon.loss.HuberLoss(rho=self._cfg.train_hp.rcnn_smoothl1_rho) # == smoothl1
self.rcnn_box_loss = gluon.loss.HuberLoss(
rho=self._cfg.train_hp.rcnn_smoothl1_rho) # == smoothl1
self.metrics = [mx.metric.Loss('RPN_Conf'),
mx.metric.Loss('RPN_SmoothL1'),
mx.metric.Loss('RCNN_CrossEntropy'),
Expand Down
You are viewing a condensed version of this merge commit. You can view the full changes here.