Faster_RCNN_for_Open_Images_Dataset_Keras icon indicating copy to clipboard operation
Faster_RCNN_for_Open_Images_Dataset_Keras copied to clipboard

Published 20 hours ago • verified publisher icon RockyXu66

ValueError: Dimensions must be equal

Open Tanvi27 opened this issue 4 years ago • 2 comments

Hi, While executing training model I am facing value error ValueError. Below is the error: ValueError: Dimensions must be equal, but are 37 and 18 for '{{node rpn_loss_cls_fixed_num/mul}} = Mul[T=DT_FLOAT](rpn_loss_cls_fixed_num/strided_slice_1, rpn_loss_cls_fixed_num/Log)' with input shapes: [1,37,50,9], [1,18,25,9].

Can someone please help me out with this issue?

@RockyXu66 @adimyth

Tanvi27 avatar Nov 29 '20 04:11 Tanvi27

Hi, I am getting the same error. Were you able to resolve this error?

NaisargiOza avatar Dec 01 '20 08:12 NaisargiOza

Are you using custom data ?

Sylv-Lej avatar Dec 28 '20 15:12 Sylv-Lej