def base(self, images, is_training):
self.images = images
keep_prob = tf.cond(is_training, lambda: tf.constant(0.5),
lambda: tf.constant(1.0))
self.conv_1 = conv2d("conv_1",
images,
filters=64,
kernel_size=7,
strides=2,
activation=self.leaky_relu)
self.pool_2 = max_pooling2d("pool_2",
self.conv_1,
pool_size=2,
strides=2)
self.conv_3 = conv2d("conv_3",
self.pool_2,
filters=192,
kernel_size=3,
activation=self.leaky_relu)
self.pool_4 = max_pooling2d("pool_4",
self.conv_3,
pool_size=2,
strides=2)
self.conv_5 = conv2d("conv_5",
self.pool_4,
filters=128,
kernel_size=1,
activation=self.leaky_relu)
self.conv_6 = conv2d("conv_6",
self.conv_5,
filters=256,
kernel_size=3,
activation=self.leaky_relu)
self.conv_7 = conv2d("conv_7",
self.conv_6,
filters=256,
kernel_size=1,
activation=self.leaky_relu)
self.conv_8 = conv2d("conv_8",
self.conv_7,
filters=512,
kernel_size=3,
activation=self.leaky_relu)
self.pool_9 = max_pooling2d("pool_9",
self.conv_8,
pool_size=2,
strides=2)
self.conv_10 = conv2d("conv_10",
self.pool_9,
filters=256,
kernel_size=1,
activation=self.leaky_relu)
self.conv_11 = conv2d("conv_11",
self.conv_10,
filters=512,
kernel_size=3,
activation=self.leaky_relu)
self.conv_12 = conv2d("conv_12",
self.conv_11,
filters=256,
kernel_size=1,
activation=self.leaky_relu)
self.conv_13 = conv2d("conv_13",
self.conv_12,
filters=512,
kernel_size=3,
activation=self.leaky_relu)
self.conv_14 = conv2d("conv_14",
self.conv_13,
filters=256,
kernel_size=1,
activation=self.leaky_relu)
self.conv_15 = conv2d("conv_15",
self.conv_14,
filters=512,
kernel_size=3,
activation=self.leaky_relu)
self.conv_16 = conv2d("conv_16",
self.conv_15,
filters=256,
kernel_size=1,
activation=self.leaky_relu)
self.conv_17 = conv2d("conv_17",
self.conv_16,
filters=512,
kernel_size=3,
activation=self.leaky_relu)
self.conv_18 = conv2d("conv_18",
self.conv_17,
filters=512,
kernel_size=1,
activation=self.leaky_relu)
self.conv_19 = conv2d("conv_19",
self.conv_18,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.pool_20 = max_pooling2d("pool_20",
self.conv_19,
pool_size=2,
strides=2)
self.conv_21 = conv2d("conv_21",
self.pool_20,
filters=512,
kernel_size=1,
activation=self.leaky_relu)
self.conv_22 = conv2d("conv_22",
self.conv_21,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.conv_23 = conv2d("conv_23",
self.conv_22,
filters=512,
kernel_size=1,
activation=self.leaky_relu)
self.conv_24 = conv2d("conv_24",
self.conv_23,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.conv_25 = conv2d("conv_25",
self.conv_24,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.conv_26 = conv2d("conv_26",
self.conv_25,
filters=1024,
kernel_size=3,
strides=2,
activation=self.leaky_relu)
self.conv_27 = conv2d("conv_27",
self.conv_26,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.conv_28 = conv2d("conv_28",
self.conv_27,
filters=1024,
kernel_size=3,
activation=self.leaky_relu)
self.fc_29 = fully_connected("fc_29",
self.conv_28,
filters=512,
activation=self.leaky_relu)
self.fc_30 = fully_connected("fc_30",
self.fc_29,
filters=4096,
activation=self.leaky_relu)
self.dropout_31 = tf.nn.dropout(self.fc_30, keep_prob)
output_size = (self.cell_size * self.cell_size) * (
self.num_classes + self.boxes_per_cell * 5)
self.fc_32 = fully_connected("fc_32",
self.dropout_31,
filters=output_size,
activation=None)
return self.fc_32
def base(self, images, is_training):
if self.data_format == "NCHW":
channel_data_format = "channels_first"
elif self.data_format == "NHWC":
channel_data_format = "channels_last"
else:
raise RuntimeError(
"data format {} shodul be in ['NCHW', 'NHWC]'.".format(
self.data_format))
self.inputs = self.images = images
self.block_1 = darknet_block(
"block_1",
self.inputs,
filters=32,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.pool_1 = max_pooling2d("pool_1",
self.block_1,
pool_size=2,
strides=2,
data_format=channel_data_format)
self.block_2 = darknet_block(
"block_2",
self.pool_1,
filters=64,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.pool_2 = max_pooling2d("pool_2",
self.block_2,
pool_size=2,
strides=2,
data_format=channel_data_format)
self.block_3 = darknet_block(
"block_3",
self.pool_2,
filters=128,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_4 = darknet_block(
"block_4",
self.block_3,
filters=64,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_5 = darknet_block(
"block_5",
self.block_4,
filters=128,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.pool_3 = max_pooling2d("pool_3",
self.block_5,
pool_size=2,
strides=2,
data_format=channel_data_format)
self.block_6 = darknet_block(
"block_6",
self.pool_3,
filters=256,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_7 = darknet_block(
"block_7",
self.block_6,
filters=128,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_8 = darknet_block(
"block_8",
self.block_7,
filters=256,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.pool_4 = max_pooling2d("pool_4",
self.block_8,
pool_size=2,
strides=2,
data_format=channel_data_format)
self.block_9 = darknet_block(
"block_9",
self.pool_4,
filters=512,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_10 = darknet_block(
"block_10",
self.block_9,
filters=256,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_11 = darknet_block(
"block_11",
self.block_10,
filters=512,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_12 = darknet_block(
"block_12",
self.block_11,
filters=256,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_13 = darknet_block(
"block_13",
self.block_12,
filters=512,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.pool_5 = max_pooling2d("pool_5",
self.block_13,
pool_size=2,
strides=2,
data_format=channel_data_format)
self.block_14 = darknet_block(
"block_14",
self.pool_5,
filters=1024,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_15 = darknet_block(
"block_15",
self.block_14,
filters=512,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_16 = darknet_block(
"block_16",
self.block_15,
filters=1024,
kernel_size=3,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_17 = darknet_block(
"block_17",
self.block_16,
filters=512,
kernel_size=1,
is_training=is_training,
activation=self.activation,
data_format=self.data_format,
)
self.block_18 = darknet_block(
"block_18",
self.block_17,
filters=1024,
kernel_size=3,
is_training=is_training,
activation=self.before_last_activation,
data_format=self.data_format,
)
kernel_initializer = tf.random_normal_initializer(mean=0.0,
stddev=0.01)
self.conv_19 = conv2d(
"conv_19",
self.block_18,
filters=self.num_classes,
kernel_size=1,
activation=None,
use_bias=True,
is_debug=self.is_debug,
kernel_initializer=kernel_initializer,
data_format=channel_data_format,
)
if self.is_debug:
self._heatmap_layer = self.conv_19
if self.data_format == "NCHW":
axis = [2, 3]
if self.data_format == "NHWC":
axis = [1, 2]
# TODO(wakisaka): global average pooling should use tf.reduce_mean()
self.pool_6 = tf.reduce_mean(self.conv_19,
axis=axis,
name="global_average_pool_6")
self.base_output = tf.reshape(self.pool_6, [-1, self.num_classes],
name="pool6_reshape")
return self.base_output