Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update infogan implementation to support modern keras api #75

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update infogan implementation to support modern keras api #75

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions InfoGAN/src/model/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
from keras.models import Model
from keras.layers.core import Flatten, Dense, Dropout, Activation, Lambda, Reshape
from keras.layers.convolutional import Conv2D, Deconv2D, ZeroPadding2D, UpSampling2D
from keras.layers import Input, merge
from keras.layers import Input
from keras.layers.merge import concatenate
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.layers.pooling import MaxPooling2D
Expand Down Expand Up @@ -41,7 +42,7 @@ def generator_upsampling(cat_dim, cont_dim, noise_dim, img_dim, bn_mode, model_n
cont_input = Input(shape=cont_dim, name="cont_input")
noise_input = Input(shape=noise_dim, name="noise_input")

gen_input = merge([cat_input, cont_input, noise_input], mode="concat")
gen_input = concatenate([cat_input, cont_input, noise_input])

x = Dense(1024)(gen_input)
x = BatchNormalization()(x)
Expand Down Expand Up @@ -102,7 +103,7 @@ def generator_deconv(cat_dim, cont_dim, noise_dim, img_dim, bn_mode, batch_size,
cont_input = Input(shape=cont_dim, name="cont_input")
noise_input = Input(shape=noise_dim, name="noise_input")

gen_input = merge([cat_input, cont_input, noise_input], mode="concat")
gen_input = concatenate([cat_input, cont_input, noise_input])

x = Dense(1024)(gen_input)
x = BatchNormalization()(x)
Expand Down Expand Up @@ -190,7 +191,7 @@ def linmax_shape(input_shape):
# Reshape Q to nbatch, 1, cont_dim[0]
x_Q_C_mean = Reshape((1, cont_dim[0]))(x_Q_C_mean)
x_Q_C_logstd = Reshape((1, cont_dim[0]))(x_Q_C_logstd)
x_Q_C = merge([x_Q_C_mean, x_Q_C_logstd], mode="concat", name="Q_cont_out", concat_axis=1)
x_Q_C = concatenate([x_Q_C_mean, x_Q_C_logstd], name="Q_cont_out", axis=1)

def minb_disc(z):
diffs = K.expand_dims(z, 3) - K.expand_dims(K.permute_dimensions(z, [1, 2, 0]), 0)
Expand All @@ -212,7 +213,7 @@ def lambda_output(input_shape):
x_mbd = M(x)
x_mbd = Reshape((num_kernels, dim_per_kernel))(x_mbd)
x_mbd = MBD(x_mbd)
x = merge([x, x_mbd], mode='concat')
x = concatenate([x, x_mbd])

# Create discriminator model
x_disc = Dense(2, activation='softmax', name="disc_out")(x)
Expand Down