You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/08/27 06:30:36 UTC
[GitHub] qingzhouzhen commented on issue #7632: pvanet infer_shape error. Arguments
qingzhouzhen commented on issue #7632: pvanet infer_shape error. Arguments
URL: https://github.com/apache/incubator-mxnet/issues/7632#issuecomment-325180013
I change the config.SCALES to 1056*640, It still went wrong with the same problem, But I can print whole layers with mx.viz.print_summary(), but I change to 600*1000, it went worong, is the system fit to any config.SCALES?
below layers when I use
`mx.viz.print_summary(net, {"data":(1,3,1056,640),"gt_boxes": (1, 100, 5), "label": (1, 23760), "bbox_target": (1, 36, 66, 40), "bbox_weight": (1, 36, 66, 40)})`, it seems no concat problem, but `mx.viz.print_summary(net, {"data":(1,3,600,1000),"gt_boxes": (1, 100, 5), "label": (1, 20646), "bbox_target": (1, 36, 37, 62), "bbox_weight": (1, 36, 37, 62)})` does not work
------------------------------------------------------------------------------------------
`cls_prob(SoftmaxOutput) 1000 0 cls_score
custom34
________________________________________________________________________________________________________________________
cls_prob_reshape(Reshape) 64x1000 0 cls_prob
________________________________________________________________________________________________________________________
bbox_pred(FullyConnected) 4000 16388096 drop7
________________________________________________________________________________________________________________________
_minus75(_sub) 4000 0 bbox_pred
custom34
________________________________________________________________________________________________________________________
bbox_loss_(smooth_l1) 4000 0 _minus75
________________________________________________________________________________________________________________________
_mul75(_mul) 4000 0 custom34
bbox_loss_
________________________________________________________________________________________________________________________
bbox_loss(MakeLoss) 4000 0 _mul75
________________________________________________________________________________________________________________________
bbox_loss_reshape(Reshape) 64x4000 0 bbox_loss
________________________________________________________________________________________________________________________
label_reshape(Reshape) 64 0 custom34
________________________________________________________________________________________________________________________
blockgrad9(BlockGrad) 64 0 label_reshape
========================================================================================================================
Total params: 143975542
________________________________________________________________________________________________________________________`
.
.
.
too much to show
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services