ValueError: Dimensions must be equal
pseudo-swati opened this issue · 0 comments
pseudo-swati commented
Hi,
I've been trying to train the COCO dataset using Panoptic Deeplab along with resnet50_os32 config
but getting the following error
ValueError: Dimensions must be equal, but are 641 and 161 for '{{node DeepLabFamilyLoss/TopKGeneralLoss/sub}} = Sub[T=DT_FLOAT](IteratorGetNext:2, DeepLab/Squeeze)' with input shapes: [64,641,641], [64,161,161].
Could you please help me point to the source of the issue?