affinelayer / pix2pix-tensorflow

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/
MIT License
5.07k stars 1.3k forks source link

The second layer_specs annotation in create_generator function seems not right? #168

Open voidguy opened 5 years ago

voidguy commented 5 years ago

The original annotation is as follows: layer_specs = [ (a.ngf 8, 0.5), # decoder_8: [batch, 1, 1, ngf 8] => [batch, 2, 2, ngf 8 2] (a.ngf 8, 0.5), # decoder_7: [batch, 2, 2, ngf 8 2] => [batch, 4, 4, ngf 8 2] (a.ngf 8, 0.5), # decoder_6: [batch, 4, 4, ngf 8 2] => [batch, 8, 8, ngf 8 2] (a.ngf 8, 0.0), # decoder_5: [batch, 8, 8, ngf 8 2] => [batch, 16, 16, ngf 8 2] (a.ngf 4, 0.0), # decoder_4: [batch, 16, 16, ngf 8 2] => [batch, 32, 32, ngf 4 2] (a.ngf 2, 0.0), # decoder_3: [batch, 32, 32, ngf 4 2] => [batch, 64, 64, ngf 2 2] (a.ngf, 0.0), # decoder_2: [batch, 64, 64, ngf 2 2] => [batch, 128, 128, ngf 2] ]

how could the out_channels increased by 2?

I think the annotation should be as follows: layer_specs = [ (a.ngf 8, 0.5), # decoder_8: [batch, 1, 1, ngf 8] => [batch, 2, 2, ngf 8] (a.ngf 8, 0.5), # decoder_7: [batch, 2, 2, ngf 8 2] => [batch, 4, 4, ngf 8] (a.ngf 8, 0.5), # decoder_6: [batch, 4, 4, ngf 8 2] => [batch, 8, 8, ngf 8] (a.ngf 8, 0.0), # decoder_5: [batch, 8, 8, ngf 8 2] => [batch, 16, 16, ngf 8] (a.ngf 4, 0.0), # decoder_4: [batch, 16, 16, ngf 8 2] => [batch, 32, 32, ngf 4] (a.ngf 2, 0.0), # decoder_3: [batch, 32, 32, ngf 4 2] => [batch, 64, 64, ngf 2] (a.ngf, 0.0), # decoder_2: [batch, 64, 64, ngf 2 * 2] => [batch, 128, 128, ngf] ]