Double-Attention-Network icon indicating copy to clipboard operation
Double-Attention-Network copied to clipboard

This is the PyTorch implementation of Double Attention Network, NIPS 2018

Results 2 Double-Attention-Network issues
Sort by recently updated
recently updated
newest added

Hi, thank you for your reimplementation for A2-Net! It really help me a lot. It seems that the 'DoubleAttentionLayer' do not add the input 'x' and return the output 'tmpZ'...