def cifar10_sequential_c3d_selu(x, seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# conv5x5 selu + pool
conv1 = conv2d_selu(x,
size=5,
n_filters=32,
kernel_init=conv_selu_safe_initializer(x,
5,
seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
pool1 = max_pool2d(conv1, size=3, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
# conv5x5 selu + pool
conv2 = conv2d_selu(pool1,
size=5,
n_filters=64,
kernel_init=conv_selu_safe_initializer(pool1,
5,
seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
pool2 = max_pool2d(conv2, size=3, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
# conv3x3 selu + pool
conv3 = conv2d_selu(pool2,
size=3,
n_filters=128,
kernel_init=conv_selu_safe_initializer(pool2,
3,
seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
pool3 = max_pool2d(conv3, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
flat = flatten(pool3, name="flatten")
layers.append(("flatten", flat))
# dense softmax
dense1 = dense(flat,
n_units=10,
kernel_init=dense_selu_safe_initializer(flat,
seed=seed + 4),
name="dense_1")
layers.append(("logit", dense1))
prob = tf.nn.softmax(dense1, name="prob")
layers.append(("prob", prob))
return layers, variables
def mnist_sequential_dbn2d1(x, drop_rate=0.5):
"""Creates sequential neural network for MNIST. The network contains 2
batch-normalized fully-connected dense layers. Dropout layers are used
for regularization. The output probabilities are generated by one
dense layer followed by a softmax function.
Args:
x: A tensor representing the input.
Returns:
A tuple containing the layers of the network graph and additional
placeholders if any. Layers are represented as list of named tuples.
"""
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
flat = flatten(x, name="flatten")
layers.append(("flatten", flat))
fc1 = dense_bn(flat, n_units=256, is_training=training, name="fc1")
layers.append(("fc1", fc1))
dropout1 = tf.layers.dropout(fc1,
rate=drop_rate,
training=training,
seed=42,
name="dropout1")
layers.append(("dropout1", dropout1))
fc2 = dense_bn(dropout1, n_units=64, is_training=training, name="fc2")
layers.append(("fc2", fc2))
dropout2 = tf.layers.dropout(fc2,
rate=drop_rate,
training=training,
seed=42,
name="dropout2")
layers.append(("dropout2", dropout2))
fc3 = dense(dropout2,
n_units=10,
activation=None,
kernel_init=Kumar_initializer(activation=None),
name="fc3")
layers.append(("fc3", fc3))
prob = tf.nn.softmax(fc2, name="prob")
layers.append(("prob", prob))
return layers, variables
def auxiliary_classifier(inputs,
pool=avg_pool2d,
pool_size=5,
pool_stride=3,
n_filters_1x1=128,
n_units=1024,
drop_rate=0.7,
seed=42,
is_training=False,
regularizer_conv=None,
regularizer_dense=None,
kernel_init_conv=He_normal(seed=42),
kernel_init_dense=He_normal(seed=42),
name="inception_auxiliary_classifier"):
with tf.variable_scope(name):
# pool
pool = pool(inputs,
size=pool_size,
stride=pool_stride,
padding="VALID",
name="pool")
# 1x1
x_1x1 = conv2d_relu(pool,
size=1,
n_filters=n_filters_1x1,
stride=1,
regularizer=regularizer_conv,
kernel_init=kernel_init_conv,
name="conv_1x1")
# dense
flat = flatten(x_1x1, name="flatten")
dense = dense_relu(flat,
n_units=n_units,
regularizer=regularizer_dense,
kernel_init=kernel_init_dense,
name="dense")
# dropout
if drop_rate > 0.0:
dense = tf.layers.dropout(dense,
rate=drop_rate,
training=is_training,
seed=seed,
name="dropout")
return dense
def auxiliary_classifier_bn(inputs,
pool=avg_pool2d,
pool_size=5,
pool_stride=3,
n_filters_1x1=128,
n_units=1024,
is_training=False,
regularizer_conv=None,
regularizer_dense=None,
kernel_init_conv=He_normal(seed=42),
kernel_init_dense=He_normal(seed=42),
name="inception_auxiliary_classifier_batchnorm"):
with tf.variable_scope(name):
# pool
pool = pool(inputs,
size=pool_size,
stride=pool_stride,
padding="VALID",
name="pool")
# 1x1
x_1x1 = conv2d_bn_relu(inputs,
size=1,
n_filters=n_filters_1x1,
stride=1,
is_training=is_training,
regularizer=regularizer_conv,
kernel_init=kernel_init_conv,
name="conv_1x1")
# dense
flat = flatten(x_1x1, name="flatten")
dense = dense_bn_relu(flat,
n_units=n_units,
is_training=is_training,
regularizer=regularizer_dense,
kernel_init=kernel_init_dense,
name="dense")
return dense
def mnist_siamese_base(x, training=False, weight_decay=0.0001, seed=42):
layers = []
variables = []
conv1 = conv2d_relu(
x,
size=7,
n_filters=32,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 1),
name="conv1")
layers.append(("conv1", conv1))
pool1 = max_pool2d(conv1, size=2, stride=2, name="pool1")
layers.append(("pool1", pool1)) # 14x14
conv2 = conv2d_relu(
pool1,
size=5,
n_filters=64,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 2),
name="conv2")
layers.append(("conv2", conv2))
pool2 = max_pool2d(conv2, size=2, stride=2, name="pool2")
layers.append(("pool2", pool2)) # 7x7
conv3 = conv2d_relu(
pool2,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 3),
name="conv3")
layers.append(("conv3", conv3))
pool3 = max_pool2d(conv3, size=2, stride=2, name="pool3")
layers.append(("pool3", pool3)) # 4x4
conv4 = conv2d_relu(
pool3,
size=1,
n_filters=256,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 4),
name="conv4")
layers.append(("conv4", conv4))
pool4 = max_pool2d(conv4, size=2, stride=2, name="pool4")
layers.append(("pool4", pool4)) # 2x2
conv5 = conv2d(pool4,
size=1,
n_filters=2,
kernel_init=He_normal(seed=seed + 5),
name="conv5")
layers.append(("conv5", conv5))
pool5 = max_pool2d(conv5, size=2, stride=2, name="pool5")
layers.append(("pool5", pool5)) # 1x1
flat1 = flatten(pool5, name="flatten1")
layers.append(("output", flat1))
return layers, variables
def cifar10_sequential_c5d3_selu_drop_wd(x,
drop_rate=0.05,
weight_decay=0.001,
seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# 2x conv3x3 selu + pool
conv1 = conv2d_selu(
x,
size=5,
n_filters=64,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=conv_selu_safe_initializer(x, 5, seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
pool1 = max_pool2d(conv1, size=3, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
# 2x conv3x3 selu + pool
conv2 = conv2d_selu(
pool1,
size=5,
n_filters=64,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=conv_selu_safe_initializer(pool1, 5, seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
pool2 = max_pool2d(conv2, size=3, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
# 2x conv3x3 selu + pool
conv3 = conv2d_selu(
pool2,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=conv_selu_safe_initializer(pool2, 3, seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
conv4 = conv2d_selu(
conv3,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=conv_selu_safe_initializer(conv3, 3, seed=seed + 4),
name="conv_4")
layers.append(("conv_4", conv4))
conv5 = conv2d_selu(
conv4,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=conv_selu_safe_initializer(conv4, 3, seed=seed + 5),
name="conv_5")
layers.append(("conv_5", conv5))
pool3 = max_pool2d(conv5, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
flat = flatten(pool3, name="flatten")
layers.append(("flatten", flat))
dense1 = dense_selu(
flat,
n_units=384,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=dense_selu_safe_initializer(flat, seed=seed + 6),
name="dense_1")
layers.append(("dense_1", dense1))
if drop_rate > 0.0:
dense1 = dropout_selu(dense1,
rate=drop_rate,
training=training,
seed=seed + 7)
dense2 = dense_selu(
dense1,
n_units=192,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=dense_selu_safe_initializer(dense1, seed=seed + 8),
name="dense_2")
layers.append(("dense_2", dense2))
if drop_rate > 0.0:
dense2 = dropout_selu(dense2,
rate=drop_rate,
training=training,
seed=seed + 9)
# dense softmax
dense3 = dense(dense2,
n_units=10,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=dense_selu_safe_initializer(dense2,
seed=seed + 4),
name="dense_3")
layers.append(("logit", dense3))
prob = tf.nn.softmax(dense3, name="prob")
layers.append(("prob", prob))
return layers, variables
def cifar10_sequential_clrn5d3_wd(x,
drop_rate=0.5,
weight_decay=0.001,
seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# 2x conv3x3 selu + pool
conv1 = conv2d_relu(
x,
size=5,
n_filters=64,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
norm1 = tf.nn.lrn(conv1,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_1")
layers.append(("norm_1", norm1))
pool1 = max_pool2d(norm1, size=3, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
# 2x conv3x3 selu + pool
conv2 = conv2d_relu(
pool1,
size=5,
n_filters=64,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
norm2 = tf.nn.lrn(conv2,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_2")
layers.append(("norm_2", norm2))
pool2 = max_pool2d(norm2, size=3, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
# 2x conv3x3 selu + pool
conv3 = conv2d_relu(
pool2,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
norm3 = tf.nn.lrn(conv3,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_3")
layers.append(("norm_3", norm3))
conv4 = conv2d_relu(
norm3,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 4),
name="conv_4")
layers.append(("conv_4", conv4))
norm4 = tf.nn.lrn(conv4,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_1")
layers.append(("norm_4", norm4))
conv5 = conv2d_relu(
norm4,
size=3,
n_filters=128,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 5),
name="conv_5")
layers.append(("conv_5", conv5))
norm5 = tf.nn.lrn(conv5,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_5")
layers.append(("norm_5", norm5))
pool3 = max_pool2d(norm5, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
flat = flatten(pool3, name="flatten")
layers.append(("flatten", flat))
dense1 = dense_relu(
flat,
n_units=384,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 6),
name="dense_1")
layers.append(("dense_1", dense1))
if drop_rate > 0.0:
dense1 = tf.layers.dropout(dense1,
rate=drop_rate,
training=training,
seed=seed + 6,
name="dropout_1")
dense2 = dense_relu(
dense1,
n_units=192,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 7),
name="dense_2")
layers.append(("dense_2", dense2))
if drop_rate > 0.0:
dense2 = tf.layers.dropout(dense2,
rate=drop_rate,
training=training,
seed=seed + 7,
name="dropout_2")
# dense softmax
dense3 = dense(dense2,
n_units=10,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=Kumar_normal(activation=None,
mode="FAN_IN",
seed=seed + 8),
name="dense_3")
layers.append(("logit", dense3))
prob = tf.nn.softmax(dense3, name="prob")
layers.append(("prob", prob))
return layers, variables
def cifar10_sequential_cbn6d_wd(x,
drop_rate_1=0.2,
drop_rate_2=0.3,
drop_rate_3=0.4,
weight_decay=0.0001,
seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# 2x conv3x3 relu batch-norm + pool
conv1 = conv2d_relu_bn(
x,
size=3,
n_filters=32,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
conv2 = conv2d_relu_bn(
conv1,
size=3,
n_filters=32,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
pool1 = max_pool2d(conv2, size=2, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
dropout1 = tf.layers.dropout(pool1,
rate=drop_rate_1,
training=training,
seed=seed + 2,
name="dropout_1")
layers.append(("dropout_1", dropout1))
# 2x conv3x3 relu batch-norm + pool
conv3 = conv2d_relu_bn(
dropout1,
size=3,
n_filters=64,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
conv4 = conv2d_relu_bn(
conv3,
size=3,
n_filters=64,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 4),
name="conv_4")
layers.append(("conv_4", conv4))
pool2 = max_pool2d(conv4, size=2, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
dropout2 = tf.layers.dropout(pool2,
rate=drop_rate_2,
training=training,
seed=seed + 4,
name="dropout_2")
layers.append(("dropout_2", dropout2))
# 2x conv3x3 relu batch-norm + pool
conv5 = conv2d_relu_bn(
dropout2,
size=3,
n_filters=128,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 5),
name="conv_5")
layers.append(("conv_5", conv5))
conv6 = conv2d_relu_bn(
conv5,
size=3,
n_filters=128,
is_training=training,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=He_normal(seed=seed + 6),
name="conv_6")
layers.append(("conv_6", conv6))
pool3 = max_pool2d(conv6, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
dropout3 = tf.layers.dropout(pool3,
rate=drop_rate_3,
training=training,
seed=seed + 6,
name="dropout_3")
layers.append(("dropout_3", dropout3))
flat = flatten(dropout3, name="flatten")
layers.append(("flatten", flat))
# dense softmax
dense1 = dense(flat,
n_units=10,
regularizer=tf.contrib.layers.l2_regularizer(weight_decay),
kernel_init=Kumar_normal(activation=None,
mode="FAN_IN",
seed=seed + 7),
name="dense_1")
layers.append(("logit", dense1))
prob = tf.nn.softmax(dense1, name="prob")
layers.append(("prob", prob))
return layers, variables
def cifar10_sequential_cbn3d(x,
drop_rate_1=0.2,
drop_rate_2=0.3,
drop_rate_3=0.4,
seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# conv5x5 batch-norm relu + pool
conv1 = conv2d_bn_relu(x,
size=5,
n_filters=32,
is_training=training,
kernel_init=He_normal(seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
pool1 = max_pool2d(conv1, size=3, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
dropout1 = tf.layers.dropout(pool1,
rate=drop_rate_1,
training=training,
seed=seed + 1,
name="dropout_1")
layers.append(("dropout_1", dropout1))
# conv5x5 batch-norm relu + pool
conv2 = conv2d_bn_relu(dropout1,
size=5,
n_filters=64,
is_training=training,
kernel_init=He_normal(seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
pool2 = max_pool2d(conv2, size=3, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
dropout2 = tf.layers.dropout(pool2,
rate=drop_rate_2,
training=training,
seed=seed + 2,
name="dropout_2")
layers.append(("dropout_2", dropout2))
# conv3x3 batch-norm relu + pool
conv3 = conv2d_bn_relu(dropout2,
size=3,
n_filters=128,
is_training=training,
kernel_init=He_normal(seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
pool3 = max_pool2d(conv3, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
dropout3 = tf.layers.dropout(pool3,
rate=drop_rate_3,
training=training,
seed=seed + 3,
name="dropout_3")
layers.append(("dropout_3", dropout3))
flat = flatten(dropout3, name="flatten")
layers.append(("flatten", flat))
# dense softmax
dense1 = dense(flat,
n_units=10,
kernel_init=Kumar_normal(activation=None,
mode="FAN_IN",
seed=seed + 4),
name="dense_1")
layers.append(("logit", dense1))
prob = tf.nn.softmax(dense1, name="prob")
layers.append(("prob", prob))
return layers, variables
def cifar10_sequential_clrn3d(x,
drop_rate_1=0.2,
drop_rate_2=0.3,
drop_rate_3=0.4,
seed=42):
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
# conv5x5 relu + lrn + pool
conv1 = conv2d_relu(x,
size=5,
n_filters=32,
kernel_init=tf.truncated_normal_initializer(
stddev=5e-2, seed=seed + 1),
name="conv_1")
layers.append(("conv_1", conv1))
norm1 = tf.nn.lrn(conv1,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_1")
layers.append(("norm_1", norm1))
pool1 = max_pool2d(norm1, size=3, stride=2, name="pool_1")
layers.append(("pool_1", pool1))
dropout1 = tf.layers.dropout(pool1,
rate=drop_rate_1,
training=training,
seed=seed + 1,
name="dropout_1")
layers.append(("dropout_1", dropout1))
# conv5x5 relu + lrn + pool
conv2 = conv2d_relu(dropout1,
size=5,
n_filters=64,
kernel_init=tf.truncated_normal_initializer(
stddev=5e-2, seed=seed + 2),
name="conv_2")
layers.append(("conv_2", conv2))
norm2 = tf.nn.lrn(conv2,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_2")
layers.append(("norm_2", norm2))
pool2 = max_pool2d(norm2, size=3, stride=2, name="pool_2")
layers.append(("pool_2", pool2))
dropout2 = tf.layers.dropout(pool2,
rate=drop_rate_2,
training=training,
seed=seed + 2,
name="dropout_2")
layers.append(("dropout_2", dropout2))
# conv3x3 relu + lrn + pool
conv3 = conv2d_relu(dropout2,
size=3,
n_filters=128,
kernel_init=tf.truncated_normal_initializer(
stddev=5e-2, seed=seed + 3),
name="conv_3")
layers.append(("conv_3", conv3))
norm3 = tf.nn.lrn(conv3,
depth_radius=4,
bias=1.0,
alpha=0.001 / 9.0,
beta=0.75,
name="norm_3")
layers.append(("norm_3", norm3))
pool3 = max_pool2d(norm3, size=2, stride=2, name="pool_3")
layers.append(("pool_3", pool3))
dropout3 = tf.layers.dropout(pool3,
rate=drop_rate_3,
training=training,
seed=seed + 3,
name="dropout_3")
layers.append(("dropout_3", dropout3))
flat = flatten(dropout3, name="flatten")
layers.append(("flatten", flat))
# dense softmax
dense1 = dense(flat,
n_units=10,
kernel_init=tf.truncated_normal_initializer(stddev=1 /
192.0,
seed=seed + 4),
name="dense_1")
layers.append(("logit", dense1))
prob = tf.nn.softmax(dense1, name="prob")
layers.append(("prob", prob))
return layers, variables
def mnist_sequential_c2d2(x, drop_rate=0.5):
"""Creates sequential convolutional neural network for MNIST. The network
uses 2 convolutional+pooling layers to create the representation part
of the network, and 1 fully-connected dense layer to create the
classifier part. Dropout layer is used for regularization. The output
probabilities are generated by one dense layer followed by a softmax
function.
Args:
x: A tensor representing the input.
Returns:
A tuple containing the layers of the network graph and additional
placeholders if any. Layers are represented as list of named tuples.
"""
layers = []
variables = []
training = tf.placeholder(tf.bool, name="training")
variables.append(("training", training))
conv1 = conv2d(x,
size=5,
n_filters=32,
kernel_init=Kumar_initializer(mode="FAN_AVG"),
name="conv1")
layers.append(("conv1", conv1))
pool1 = max_pool(conv1, name="pool1")
layers.append(("pool1", pool1))
conv2 = conv2d(pool1,
size=5,
n_filters=64,
kernel_init=Kumar_initializer(mode="FAN_IN"),
name="conv2")
layers.append(("conv2", conv2))
pool2 = max_pool(conv2, name="pool2")
layers.append(("pool2", pool2))
flat = flatten(pool2, name="flatten")
layers.append(("flatten", flat))
fc1 = dense(flat,
n_units=1024,
kernel_init=Kumar_initializer(mode="FAN_IN"),
name="fc1")
layers.append(("fc1", fc1))
dropout1 = tf.layers.dropout(fc1,
rate=drop_rate,
training=training,
seed=42,
name="dropout")
layers.append(("dropout1", dropout1))
fc2 = dense(dropout1,
n_units=10,
activation=None,
kernel_init=Kumar_initializer(activation=None, mode="FAN_IN"),
name="fc2")
layers.append(("fc2", fc2))
prob = tf.nn.softmax(fc2, name="prob")
layers.append(("prob", prob))
return layers, variables
