Recurrent-Attention-CNN Implement RA-CNN in tensorflow

Implement RA-CNN in tensorflow

Open Kongsea opened this issue 7 years ago • 6 comments

How to implement formular (4) in the paper? If we have the three tensors, tx, ty and tl with the shape (None, 1) respectively, how do we get the corresponding mask M?

In python, we can use two loops as: for x in tx: for y in ty: mask[x, y] = hx(x, y)

Then how to implement this in TensorFlow? Thank you.

Dec 18 '17 12:12 Kongsea

Maybe we need tensor operations or broadcasting? I'm not very familiar with that.

Dec 18 '17 12:12 Kongsea

It seems it's my fault. I have used an image with unequal width and height, so it caused error when calculating Mask.

Dec 19 '17 01:12 Kongsea

@Kongsea Is it convenient for you to leave a contact?for qq or others

Dec 28 '17 05:12 cocowf

who has implemented the network by tensorflow?

Jan 25 '18 06:01 felix-duan

@cocowf @felix-duan Do you have implemented the network by tensorflow? I have some trouble in APN ,and I described my question in Issue area. Could you please help me?

May 23 '18 06:05 Ostnie

Do you have implemented the network by tensorflow? @cocowf @felix-duan @Ostnie

Jul 16 '18 12:07 XZNWU

Recurrent-Attention-CNN Recurrent-Attention-CNN copied to clipboard

Implement RA-CNN in tensorflow

Recurrent-Attention-CNN
Recurrent-Attention-CNN copied to clipboard