Quantcast
Channel: How to design n-dimensional feature descriptor similar as the input image? - Data Science Stack Exchange
Browsing all 2 articles
Browse latest View live

Answer by Ali Raza Memon for How to design n-dimensional feature descriptor...

The problem was with the tf.reshape. Instead I replaced it with pd_input = Reshape((2, 2, 256))(p_encoder). Finally I got the desired output which is same as input (265, 256, 3).

View Article



How to design n-dimensional feature descriptor similar as the input image?

I am re-writing the H-Net code in Keras for cross-domain image similarity. The network architecture is described in the attached paper. I wrote the encoder and decoder parts but unable to get similar...

View Article
Browsing all 2 articles
Browse latest View live




Latest Images