def build(self):
"""Create the network graph."""
# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
conv1 = conv(self.x, 11, 11, 96, 4, 4, padding='VALID', name='conv1')
norm1 = lrn(conv1, 2, 1e-05, 0.75, name='norm1')
pool1 = max_pool(norm1, 3, 3, 2, 2, padding='VALID', name='pool1')
# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool with 2 groups
conv2 = conv(pool1, 5, 5, 256, 1, 1, groups=2, name='conv2')
norm2 = lrn(conv2, 2, 1e-05, 0.75, name='norm2')
pool2 = max_pool(norm2, 3, 3, 2, 2, padding='VALID', name='pool2')
# 3rd Layer: Conv (w ReLu)
conv3 = conv(pool2, 3, 3, 384, 1, 1, name='conv3')
# 4th Layer: Conv (w ReLu) splitted into two groups
conv4 = conv(conv3, 3, 3, 384, 1, 1, groups=2, name='conv4')
# 5th Layer: Conv (w ReLu) -> Pool splitted into two groups
conv5 = conv(conv4, 3, 3, 256, 1, 1, groups=2, name='conv5')
pool5 = max_pool(conv5, 3, 3, 2, 2, padding='VALID', name='pool5')
# 6th Layer: Flatten -> FC (w ReLu) -> Dropout
flattened = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc6 = fc(flattened, 6 * 6 * 256, 4096, name='fc6')
# 7th Layer: FC (w ReLu) -> Dropout
fc7 = fc(fc6, 4096, 4096, name='fc7')
# 8th Layer: FC and return unscaled activations
self.fc8 = fc(fc7, 4096, self.num_classes, relu=False, name='fc8')
def build_graph(self):
self.iterator = tf.data.Iterator.from_structure(
(tf.float32, tf.int32),
(tf.TensorShape([None, 227, 227, 3]), tf.TensorShape([None]))
)
self.inputs, self.labels = self.iterator.get_next()
self.conv1 = layers.conv(self.inputs, [11, 11], 96, [4, 4],
padding='VALID', name='conv1', mask=True)
norm1 = layers.lrn(self.conv1, 2, 1e-05, 0.75, name='norm1')
pool1 = layers.max_pool(norm1, [3, 3], [2, 2], padding='VALID',
name='pool1')
self.conv2 = layers.conv(pool1, [5, 5], 256, [1, 1], groups=2,
name='conv2', mask=True)
norm2 = layers.lrn(self.conv2, 2, 1e-05, 0.75, name='norm2')
pool2 = layers.max_pool(norm2, [3, 3], [2, 2], padding='VALID',
name='pool2')
self.conv3 = layers.conv(pool2, [3, 3], 384, [1, 1], name='conv3',
mask=True)
self.conv4 = layers.conv(self.conv3, [3, 3], 384, [1, 1], groups=2,
name='conv4', mask=True)
self.conv5 = layers.conv(self.conv4, [3, 3], 256, [1, 1], groups=2,
name='conv5', mask=True)
pool5 = layers.max_pool(self.conv5, [3, 3], [2, 2], padding='VALID',
name='pool5')
self.keep_prob = tf.get_variable('keep_prob', shape=(),
trainable=False)
flattened = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc6 = layers.fc(flattened, 4096, name='fc6')
dropout6 = layers.dropout(fc6, self.keep_prob)
fc7 = layers.fc(dropout6, 4096, name='fc7')
dropout7 = layers.dropout(fc7, self.keep_prob)
self.logits = layers.fc(dropout7, self.num_classes, relu=False,
name='fc8')
self.probs_op = tf.nn.softmax(self.logits)
self.pred_op = tf.argmax(input=self.logits, axis=1)
corrects_op = tf.equal(tf.cast(self.pred_op, tf.int32),
self.labels)
self.acc_op = tf.reduce_mean(tf.cast(corrects_op, tf.float32))
def _build_graph(self):
self.x = tf.placeholder(tf.float32, [None, 227, 227, 3])
self.y = tf.placeholder(tf.float32, [None, 2])
self.keep_prob = tf.placeholder_with_default(1.0,
shape=[],
name='dropout_keep_prob')
# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
conv1 = conv(self.x, 11, 11, 96, 4, 4, padding='VALID', name='conv1')
norm1 = lrn(conv1, 2, 1e-05, 0.75, name='norm1')
pool1 = max_pool(norm1, 3, 3, 2, 2, padding='VALID', name='pool1')
# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool with 2 groups
conv2 = conv(pool1, 5, 5, 256, 1, 1, groups=2, name='conv2')
norm2 = lrn(conv2, 2, 1e-05, 0.75, name='norm2')
pool2 = max_pool(norm2, 3, 3, 2, 2, padding='VALID', name='pool2')
# 3rd Layer: Conv (w ReLu)
conv3 = conv(pool2, 3, 3, 384, 1, 1, name='conv3')
# 4th Layer: Conv (w ReLu) split into two groups
conv4 = conv(conv3, 3, 3, 384, 1, 1, groups=2, name='conv4')
# 5th Layer: Conv (w ReLu) -> Pool split into two groups
conv5 = conv(conv4, 3, 3, 256, 1, 1, groups=2, name='conv5')
pool5 = max_pool(conv5, 3, 3, 2, 2, padding='VALID', name='pool5')
# 6th Layer: Flatten -> FC (w ReLu) -> Dropout
flattened = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc6 = fc(flattened, 6 * 6 * 256, 4096, name='fc6')
dropout6 = dropout(fc6, self.keep_prob)
# 7th Layer: FC (w ReLu) -> Dropout
fc7 = fc(dropout6, 4096, 4096, name='fc7')
dropout7 = dropout(fc7, self.keep_prob)
# 8th Layer: FC and return unscaled activations
self.fc8 = fc(dropout7, 4096, self.num_classes, relu=False, name='fc8')
self.prob = tf.nn.softmax(self.fc8, name='prob')
def build(self):
"""Create the network graph."""
# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
conv1 = conv(self.x, 11, 11, 96, 4, 4, padding='VALID', name='conv1')
norm1 = lrn(conv1, 2, 1e-05, 0.75, name='norm1')
pool1 = max_pool(norm1, 3, 3, 2, 2, padding='VALID', name='pool1')
# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool with 2 groups
conv2 = conv(pool1, 5, 5, 256, 1, 1, groups=2, name='conv2')
norm2 = lrn(conv2, 2, 1e-05, 0.75, name='norm2')
pool2 = max_pool(norm2, 3, 3, 2, 2, padding='VALID', name='pool2')
# 3rd Layer: Conv (w ReLu)
conv3 = conv(pool2, 3, 3, 384, 1, 1, name='conv3')
# 4th Layer: Conv (w ReLu) splitted into two groups
conv4 = conv(conv3, 3, 3, 384, 1, 1, groups=2, name='conv4')
# 5th Layer: Conv (w ReLu) -> Pool splitted into two groups
conv5 = conv(conv4, 3, 3, 256, 1, 1, groups=2, name='conv5')
pool5 = max_pool(conv5, 3, 3, 2, 2, padding='VALID', name='pool5')
# 6th Layer: Flatten -> FC (w ReLu) -> Dropout
flattened = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc6 = fc(flattened, 6 * 6 * 256, 4096, name='fc6')
fc7_factor = fc(fc6, 4096, self.num_factor_units, 'fc7_factor')
fc7_shared = fc(fc6, 4096, 4096 - self.num_factor_units, 'fc7_shared')
with tf.variable_scope('fc7_factor', reuse=True):
self.assign_factor = tf.group(tf.get_variable('weights').assign(self.factor_weights),
tf.get_variable('biases').assign(self.factor_biases))
fc7_concat = tf.concat([fc7_factor, fc7_shared], axis=1, name='fc7_concat')
# 8th Layer: FC and return unscaled activations
self.fc8 = fc(fc7_concat, 4096, self.num_classes, relu=False, name='fc8')
def _build_graph(self):
self.x = tf.placeholder(tf.float32, [None, 227, 227, 3])
self.y = tf.placeholder(tf.float32, [None, 2])
if self.factor_layer == 'conv1':
self.factor_weights = tf.placeholder(
tf.float32, shape=[11, 11, 3, self.num_factors])
elif self.factor_layer == 'conv3':
self.factor_weights = tf.placeholder(
tf.float32, shape=[3, 3, 128, self.num_factors])
elif self.factor_layer == 'conv5':
self.factor_weights = tf.placeholder(
tf.float32, shape=[3, 3, 192, self.num_factors])
elif self.factor_layer == 'fc7':
self.factor_weights = tf.placeholder(
tf.float32, shape=[4096, self.num_factors])
self.factor_biases = tf.placeholder(tf.float32,
shape=[self.num_factors])
# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
if self.factor_layer == 'conv1':
conv1_factor = conv(self.x,
11,
11,
self.num_factors,
4,
4,
padding='VALID',
name='conv1_factor')
conv1_shared = conv(self.x,
11,
11,
96 - self.num_factors,
4,
4,
padding='VALID',
name='conv1_shared')
splits = tf.split(axis=3, num_or_size_splits=2, value=conv1_factor)
conv1 = tf.concat([splits[0], conv1_shared, splits[1]],
axis=3,
name='conv1_concat')
else:
conv1 = conv(self.x,
11,
11,
96,
4,
4,
padding='VALID',
name='conv1')
norm1 = lrn(conv1, 2, 1e-05, 0.75, name='norm1')
pool1 = max_pool(norm1, 3, 3, 2, 2, padding='VALID', name='pool1')
# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool with 2 groups
conv2 = conv(pool1, 5, 5, 256, 1, 1, groups=2, name='conv2')
norm2 = lrn(conv2, 2, 1e-05, 0.75, name='norm2')
pool2 = max_pool(norm2, 3, 3, 2, 2, padding='VALID', name='pool2')
# 3rd Layer: Conv (w ReLu)
if self.factor_layer == 'conv3':
conv3_factor = conv(pool2,
3,
3,
self.num_factors,
1,
1,
groups=2,
name='conv3_factor')
conv3_shared = conv(pool2,
3,
3,
384 - self.num_factors,
1,
1,
name='conv3_shared')
splits = tf.split(axis=3, num_or_size_splits=2, value=conv3_factor)
conv3 = tf.concat([splits[0], conv3_shared, splits[1]],
axis=3,
name='conv3_concat')
else:
conv3 = conv(pool2, 3, 3, 384, 1, 1, name='conv3')
# 4th Layer: Conv (w ReLu) split into two groups
conv4 = conv(conv3, 3, 3, 384, 1, 1, groups=2, name='conv4')
# 5th Layer: Conv (w ReLu) -> Pool split into two groups
if self.factor_layer == 'conv5':
conv5_factor = conv(conv4,
3,
3,
self.num_factors,
1,
1,
groups=2,
name='conv5_factor')
conv5_shared = conv(conv4,
3,
3,
256 - self.num_factors,
1,
1,
groups=2,
name='conv5_shared')
splits = tf.split(axis=3, num_or_size_splits=2, value=conv5_factor)
conv5 = tf.concat([splits[0], conv5_shared, splits[1]],
axis=3,
name='conv5_concat')
else:
conv5 = conv(conv4, 3, 3, 256, 1, 1, groups=2, name='conv5')
pool5 = max_pool(conv5, 3, 3, 2, 2, padding='VALID', name='pool5')
# 6th Layer: Flatten -> FC (w ReLu)
flattened = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc6 = fc(flattened, 6 * 6 * 256, 4096, name='fc6')
if self.factor_layer == 'fc7':
fc7_factor = fc(fc6, 4096, self.num_factors, 'fc7_factor')
fc7_shared = fc(fc6, 4096, 4096 - self.num_factors, 'fc7_shared')
fc7 = tf.concat([fc7_factor, fc7_shared],
axis=1,
name='fc7_concat')
else:
fc7 = fc(fc6, 4096, 4096, name='fc7')
with tf.variable_scope('{}_factor'.format(self.factor_layer),
reuse=True):
self.assign_factor = tf.group(
tf.get_variable('weights').assign(self.factor_weights),
tf.get_variable('biases').assign(self.factor_biases))
# 8th Layer: FC and return unscaled activations
self.fc8 = fc(fc7, 4096, self.num_classes, relu=False, name='fc8')
self.prob = tf.nn.softmax(self.fc8, name='prob')