def __init__(self, sess, epoch, batch_size, z_dim, dataset_name,
checkpoint_dir, sample_dir, log_dir, mode):
self.sess = sess
self.epoch = epoch
self.batch_size = batch_size
self.checkpoint_dir = checkpoint_dir
self.sample_dir = sample_dir
self.log_dir = log_dir
self.dataset_name = dataset_name
self.z_dim = z_dim
self.random_seed = 1000
self.gamma = 10 #the scale of gradient penalty
self.lamb = 0.0002 #the scale of the distance metric used for adaptive margins
if dataset_name == 'mnist' or dataset_name == 'fashion-mnist':
#image_dimension
self.imgH = 28
self.imgW = 28
#the size of the first layer of generator
self.s_size = 3
#arguments for the last layer of generator
self.last_dconv = {
'kernel_size': [5, 5],
'stride': 1,
'padding': 'VALID'
}
#depths for convolution in generator and discriminator
self.g_depths = [512, 256, 128, 64]
self.d_depths = [64, 128, 256, 512]
#channel
self.c_dim = 1
#WGAN parameter, the number of critic iterations for each epoch
self.d_iters = 1
self.g_iters = 1
#train
self.learning_rate = 0.0002
self.beta1 = 0.5
self.beta2 = 0.9
#test, number of generated images to be saved
self.sample_num = 100
#load numpy array of images and labels
self.images = load_mnist(self.dataset_name)
elif dataset_name == 'anime':
#image_dimension
self.imgH = 64
self.imgW = 64
#the size of the first layer of generator
self.s_size = 4
#arguments for the last layer of generator, same as the general
self.last_dconv = {}
#depths for convolution in generator and discriminator
self.g_depths = [512, 256, 128, 64]
self.d_depths = [64, 128, 256, 512]
#channel dim
self.c_dim = 3
#WGAN parameter, the number of critic iterations for each epoch
self.d_iters = 1
self.g_iters = 1
#train
self.learning_rate = 0.0002
self.beta1 = 0.5
self.beta2 = 0.9
#test, number of generated images to be saved
self.sample_num = 64
self.images = load_anime(self.dataset_name)
else:
raise NotImplementedError
def __init__(self, sess, epoch, batch_size, z_dim, dataset_name,
checkpoint_dir, sample_dir, log_dir, mode):
self.sess = sess
self.epoch = epoch
self.batch_size = batch_size
self.checkpoint_dir = checkpoint_dir
self.sample_dir = sample_dir
self.log_dir = log_dir
self.dataset_name = dataset_name
self.z_dim = z_dim
self.random_seed = 1000
if dataset_name == 'mnist' or dataset_name == 'fashion-mnist':
#image_dimension
self.imgH = 28
self.imgW = 28
#feature map size of the first layer of generator
self.s_size = 7
self.g_depth = 64 #first layer
self.d_depths = [64, 128, 256, 512]
self.num_layers = 2 #how many times upsampling
#channel and label dim
self.c_dim = 1
self.y_dim = 10
self.d_iters = 2
self.g_iters = 1
self.learning_rate = 0.0002
self.beta1 = 0.5
self.beta2 = 0.999
self.LAMBDA = 5
self.BETA = 3
#test, number of generated images to be saved
self.sample_num = 100
#load numpy array of images and labels
self.images, self.labels = load_mnist(self.dataset_name)
elif dataset_name == 'anime':
#image_dimension
self.imgH = 64
self.imgW = 64
#feature map size of the first layer of generator
self.s_size = 16
self.g_depth = 64 #first layer
self.d_depths = [64, 128, 256, 512]
self.num_layers = 2 #how many times upsampling
#channel and label dim
self.c_dim = 3
self.y_dim = 22
self.d_iters = 2
self.g_iters = 1
self.learning_rate = 0.0002
self.beta1 = 0.5
self.beta2 = 0.999
self.LAMBDA = 0.05
self.BETA = 10
#test, number of generated images to be saved
self.sample_num = 64
self.images, self.labels = load_anime(self.dataset_name)
else:
raise NotImplementedError