def _make_se_score_feats(self, inputs, out_filters, training):
in_filters = get_filters(inputs, self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs, in_filters // 2,
kernel_size=1, strides=1, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs, out_filters,
kernel_size=1, strides=1, data_format=self.data_format)
return inputs
def _make_score_feats(self, inputs, training):
in_filters = get_filters(inputs, self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs,
in_filters // 2,
kernel_size=1,
strides=1,
data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = squeeze(inputs, self.data_format)
inputs = tf.layers.dense(inputs, units=self.num_classes, use_bias=True)
return tf.identity(inputs, 'final_dense')
def _make_score_feats(self, inputs, training):
in_filters = get_filters(inputs, self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs, in_filters // 2,
kernel_size=1, strides=1, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format) # 1056
inputs = conv2d_fixed_padding(inputs, 512, kernel_size=3, strides=2, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format) # 512
inputs = conv2d_fixed_padding(inputs, 128, kernel_size=1, strides=1, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs, 128, kernel_size=3, strides=1, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = conv2d_fixed_padding(inputs, 32, kernel_size=2, strides=2, data_format=self.data_format)
inputs = batch_norm_relu(inputs, training, self.data_format)
inputs = tf.reshape(inputs, [-1, 2 * 2 * 32])
fc1 = tf.add(tf.matmul(inputs, variable(128, 32)), bias([32]))
fc1 = tf.nn.relu(fc1)
fc3 = tf.add(tf.matmul(fc1, variable(32, 6)), bias([6]))
# inputs = squeeze(inputs, self.data_format)
#
# inputs = tf.layers.dense(inputs, units=6, use_bias=True)
return tf.identity(fc3, 'final_dense')
def get_scale(inputs, ratio, channels, training, data_format):
inputs = batch_norm_relu(inputs, training, data_format)
squeezed = squeeze(inputs, data_format)
scale = tf.layers.dense(squeezed, units=channels // ratio, activation=tf.nn.relu)
scale = tf.layers.dense(scale, units=channels, activation=tf.nn.sigmoid)
if data_format == 'channels_first':
scale = tf.expand_dims(scale, axis=-1)
scale = tf.expand_dims(scale, axis=-1)
else:
scale = tf.expand_dims(scale, axis=1)
scale = tf.expand_dims(scale, axis=1)
return scale