why kSize of 64 in upscore_layer

MarvinTeichmann / tensorflow-fcn

An Implementation of Fully Convolutional Networks in Tensorflow.

MIT License

1.1k stars 433 forks source link

Open yzhang123 opened 7 years ago

yzhang123 commented 7 years ago

Hi @MarvinTeichmann, I was wondering how you came about the value 64 for kSize in the upscore_layer of fcn32

Also I was wondering how you came about the bilinear value calculations for the deconv_filter?

Thanks!