def dcgan_encoder(name, inputs, n_channels, latent_dim, is_training, mode=None, nonlinearity=LeakyReLU): conv2d.set_weights_stdev(0.02) deconv2d.set_weights_stdev(0.02) linear.set_weights_stdev(0.02) output = tf.reshape(inputs, [-1, n_channels, DIM, DIM]) output = Conv2D(name + '.1', 3, DIM, 5, output, stride=2) output = nonlinearity(output) output = Conv2D(name + '.2', DIM, 2 * DIM, 5, output, stride=2) output = Normalize(name + '.BN2', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.3', 2 * DIM, 4 * DIM, 5, output, stride=2) output = Normalize(name + '.BN3', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.4', 4 * DIM, 8 * DIM, 5, output, stride=2) output = Normalize(name + '.BN4', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = tf.reshape(output, [-1, 4 * 4 * 8 * DIM]) output = Linear(name + '.Output', 4 * 4 * 8 * DIM, latent_dim, output) conv2d.unset_weights_stdev() deconv2d.unset_weights_stdev() linear.unset_weights_stdev() return output
def high_capacity_encoder(name, inputs, n_channels, latent_dim, is_training, mode=None, nonlinearity=tf.nn.relu): output = tf.reshape(inputs, [-1, n_channels, DIM, DIM]) output = Conv2D(name + '.0', n_channels, DIM, 5, output, stride=2) output = Normalize(name + '.BN0', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.1', DIM, DIM * 2, 5, output, stride=2) output = Normalize(name + '.BN1', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.2', DIM * 2, DIM * 4, 5, output, stride=2) output = Normalize(name + '.BN2', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = tf.reshape(output, [-1, DIM * 4 * 8 * 8]) output = Linear(name + '.FC', DIM * 4 * 8 * 8, DIM * 4 * 8, output) output = Normalize(name + '.BNFC', [0], output, is_training, mode) output = nonlinearity(output) output = Linear(name + '.Output', DIM * 4 * 8, latent_dim, output) return output
def high_capacity_decoder(name, z, n_channels, is_training, mode=None, nonlinearity=tf.nn.relu): output = Linear(name + '.Input', z.get_shape().as_list()[1], DIM * 4 * 8 * 8, z) output = Normalize(name + '.BN0', [0], output, is_training, mode) output = nonlinearity(output) output = tf.reshape(output, [-1, DIM * 4, 8, 8]) output = Deconv2D(name + '.1', DIM * 4, DIM * 4, 5, output) output = Normalize(name + '.BN1', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Deconv2D(name + '.2', DIM * 4, DIM * 2, 5, output) output = Normalize(name + '.BN2', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Deconv2D(name + '.3', DIM * 2, DIM // 2, 5, output) output = Normalize(name + '.BN3', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.4', DIM // 2, n_channels, 5, output) output = tf.reshape(output, [-1, n_channels * DIM * DIM]) return output
def resnet_encoder_new(name, inputs, n_channels, latent_dim, is_training, mode=None, nonlinearity=tf.nn.relu): output = tf.reshape(inputs, [-1, n_channels, DIM, DIM]) output = Conv2D(name + '.Input', n_channels, DIM, 3, output, he_init=False, cpu=CPU) output = ResidualBlock(name + '.Res1', DIM, 2 * DIM, 3, output, is_training, mode, resample='down') output = ResidualBlock(name + '.Res2', 2 * DIM, 4 * DIM, 3, output, is_training, mode, resample='down') output = ResidualBlock(name + '.Res3', 4 * DIM, 8 * DIM, 3, output, is_training, mode, resample='down') output = ResidualBlock(name + '.Res4', 8 * DIM, 8 * DIM, 3, output, is_training, mode, resample='down') output = Normalize(name + '.BN.5', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = tf.reshape(output, [-1, 4 * 4 * 8 * DIM]) output = Linear(name + '.Output', 4 * 4 * 8 * DIM, latent_dim, output) return output
def resnet_decoder(name, z, n_channels, is_training, mode=None, nonlinearity=tf.nn.relu): output = Linear(name + '.Input', z.get_shape().as_list()[1], 4 * 4 * 8 * DIM, z) output = Normalize(name + '.BN0', [0], output, is_training, mode) output = nonlinearity(output) output = tf.reshape(output, [-1, 8 * DIM, 4, 4]) output = ResidualBlock(name + '.Res1', 8 * DIM, 8 * DIM, 3, output, is_training, mode, resample='up', norm_inputs=True) output = ResidualBlock(name + '.Res2', 8 * DIM, 4 * DIM, 3, output, is_training, mode, resample='up') output = ResidualBlock(name + '.Res3', 4 * DIM, 2 * DIM, 3, output, is_training, mode, resample='up') output = ResidualBlock(name + '.Res4', 2 * DIM, 1 * DIM, 3, output, is_training, mode, resample='up') output = Normalize(name + '.BN5', [0, 2, 3], output, is_training, mode) output = nonlinearity(output) output = Conv2D(name + '.Output', DIM, n_channels, 3, output) output = tf.reshape(output, [-1, n_channels * DIM * DIM]) return output
def ConvMeanPool(name, input_dim, output_dim, filter_size, inputs, he_init=True, biases=True): output = Conv2D(name, input_dim, output_dim, filter_size, inputs, he_init=he_init, biases=biases, cpu=CPU) output = tf.add_n([ output[:, :, ::2, ::2], output[:, :, 1::2, ::2], output[:, :, ::2, 1::2], output[:, :, 1::2, 1::2] ]) / 4. return output
def UpsampleConv(name, input_dim, output_dim, filter_size, inputs, he_init=True, biases=True): output = inputs output = tf.concat([output, output, output, output], axis=1) output = tf.transpose(output, [0, 2, 3, 1]) output = tf.depth_to_space(output, 2) output = tf.transpose(output, [0, 3, 1, 2]) output = Conv2D(name, input_dim, output_dim, filter_size, output, he_init=he_init, biases=biases, cpu=CPU) return output