def get_conv_dense_model():
graph = Graph((32, 32, 3), False)
output_node_id = 0
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(StubDropout(Constant.DENSE_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(graph.node_list[output_node_id].shape[0], 5),
output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(5, 5), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
graph.produce_model().set_weight_to_graph()
return graph
def generate(self,
model_len=Constant.MODEL_LEN,
model_width=Constant.MODEL_WIDTH):
pooling_len = int(model_len / 4)
graph = Graph(self.input_shape, False)
temp_input_channel = self.input_shape[-1]
output_node_id = 0
for i in range(model_len):
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(
StubConv(temp_input_channel, model_width, kernel_size=3),
output_node_id)
output_node_id = graph.add_layer(
StubBatchNormalization(model_width), output_node_id)
temp_input_channel = model_width
if pooling_len == 0 or ((i + 1) % pooling_len == 0
and i != model_len - 1):
output_node_id = graph.add_layer(StubPooling(), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(
StubDropout(Constant.CONV_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(
StubDense(graph.node_list[output_node_id].shape[0], model_width),
output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(
StubDense(model_width, self.n_classes), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
return graph
def deeper_conv_block(conv_layer, kernel_size, weighted=True):
filter_shape = (kernel_size, ) * 2
n_filters = conv_layer.filters
weight = np.zeros((n_filters, n_filters) + filter_shape)
center = tuple(map(lambda x: int((x - 1) / 2), filter_shape))
for i in range(n_filters):
filter_weight = np.zeros((n_filters, ) + filter_shape)
index = (i, ) + center
filter_weight[index] = 1
weight[i, ...] = filter_weight
bias = np.zeros(n_filters)
new_conv_layer = StubConv(conv_layer.filters,
n_filters,
kernel_size=kernel_size)
bn = StubBatchNormalization(n_filters)
if weighted:
new_conv_layer.set_weights(
(add_noise(weight,
np.array([0, 1])), add_noise(bias, np.array([0, 1]))))
new_weights = [
add_noise(np.ones(n_filters, dtype=np.float32), np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32), np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32), np.array([0, 1])),
add_noise(np.ones(n_filters, dtype=np.float32), np.array([0, 1]))
]
bn.set_weights(new_weights)
return [StubReLU(), new_conv_layer, bn]
def dense_to_deeper_block(dense_layer, weighted=True):
units = dense_layer.units
weight = np.eye(units, dtype=np.float32)
bias = np.zeros(units, dtype=np.float32)
new_dense_layer = StubDense(units, units)
if weighted:
new_dense_layer.set_weights((add_noise(weight, np.array([0, 1])), add_noise(bias, np.array([0, 1]))))
return [StubReLU(), new_dense_layer]
def get_add_skip_model():
graph = Graph((5, 5, 3), False)
output_node_id = 0
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = output_node_id
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = graph.add_layer(StubConv(3, 3, 1), temp_node_id)
output_node_id = graph.add_layer(StubAdd(), [output_node_id, temp_node_id])
temp_node_id = output_node_id
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = graph.add_layer(StubConv(3, 3, 1), temp_node_id)
output_node_id = graph.add_layer(StubAdd(), [output_node_id, temp_node_id])
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(graph.node_list[output_node_id].shape[0], 5),
output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.DENSE_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(5, 5), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.DENSE_DROPOUT_RATE), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
graph.produce_model().set_weight_to_graph()
return graph
def dense_to_deeper_block(dense_layer, weighted=True):
units = dense_layer.units
weight = np.eye(units)
bias = np.zeros(units)
new_dense_layer = StubDense(units, units)
if weighted:
new_dense_layer.set_weights(
(add_noise(weight,
np.array([0, 1])), add_noise(bias, np.array([0, 1]))))
return [
StubReLU(), new_dense_layer,
StubDropout(Constant.DENSE_DROPOUT_RATE)
]
def to_concat_skip_model(self, start_id, end_id):
"""Add a weighted add concatenate connection from after start node to end node.
Args:
start_id: The convolutional layer ID, after which to start the skip-connection.
end_id: The convolutional layer ID, after which to end the skip-connection.
"""
self.operation_history.append(
('to_concat_skip_model', start_id, end_id))
conv_block_input_id = self._conv_block_end_node(start_id)
conv_block_input_id = self.adj_list[conv_block_input_id][0][0]
block_last_layer_input_id = self._conv_block_end_node(end_id)
# Add the pooling layer chain.
pooling_layer_list = self._get_pooling_layers(
conv_block_input_id, block_last_layer_input_id)
skip_output_id = conv_block_input_id
for index, layer_id in enumerate(pooling_layer_list):
skip_output_id = self.add_layer(
deepcopy(self.layer_list[layer_id]), skip_output_id)
block_last_layer_output_id = self.adj_list[block_last_layer_input_id][
0][0]
concat_input_node_id = self._add_node(
deepcopy(self.node_list[block_last_layer_output_id]))
self._redirect_edge(block_last_layer_input_id,
block_last_layer_output_id, concat_input_node_id)
concat_layer = StubConcatenate()
concat_layer.input = [
self.node_list[concat_input_node_id],
self.node_list[skip_output_id]
]
concat_output_node_id = self._add_node(Node(concat_layer.output_shape))
self._add_edge(concat_layer, concat_input_node_id,
concat_output_node_id)
self._add_edge(concat_layer, skip_output_id, concat_output_node_id)
concat_layer.output = self.node_list[concat_output_node_id]
self.node_list[concat_output_node_id].shape = concat_layer.output_shape
# Add the concatenate layer.
new_relu_layer = StubReLU()
concat_output_node_id = self.add_layer(new_relu_layer,
concat_output_node_id)
new_conv_layer = StubConv(
self.layer_list[start_id].filters +
self.layer_list[end_id].filters, self.layer_list[end_id].filters,
1)
concat_output_node_id = self.add_layer(new_conv_layer,
concat_output_node_id)
new_bn_layer = StubBatchNormalization(self.layer_list[end_id].filters)
self._add_edge(new_bn_layer, concat_output_node_id,
block_last_layer_output_id)
new_bn_layer.input = self.node_list[concat_output_node_id]
new_bn_layer.output = self.node_list[block_last_layer_output_id]
self.node_list[
block_last_layer_output_id].shape = new_bn_layer.output_shape
if self.weighted:
filters_end = self.layer_list[end_id].filters
filters_start = self.layer_list[start_id].filters
filter_shape = (1, ) * (
len(self.layer_list[end_id].get_weights()[0].shape) - 2)
weights = np.zeros((filters_end, filters_end) + filter_shape)
for i in range(filters_end):
filter_weight = np.zeros((filters_end, ) + filter_shape)
filter_weight[(i, 0, 0)] = 1
weights[i, ...] = filter_weight
weights = np.concatenate(
(weights,
np.zeros((filters_end, filters_start) + filter_shape)),
axis=1)
bias = np.zeros(filters_end)
new_conv_layer.set_weights((add_noise(weights, np.array([0, 1])),
add_noise(bias, np.array([0, 1]))))
n_filters = filters_end
new_weights = [
add_noise(np.ones(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.ones(n_filters, dtype=np.float32),
np.array([0, 1]))
]
new_bn_layer.set_weights(new_weights)
def to_add_skip_model(self, start_id, end_id):
"""Add a weighted add skip-connection from after start node to end node.
Args:
start_id: The convolutional layer ID, after which to start the skip-connection.
end_id: The convolutional layer ID, after which to end the skip-connection.
"""
self.operation_history.append(('to_add_skip_model', start_id, end_id))
conv_block_input_id = self._conv_block_end_node(start_id)
conv_block_input_id = self.adj_list[conv_block_input_id][0][0]
block_last_layer_input_id = self._conv_block_end_node(end_id)
# Add the pooling layer chain.
layer_list = self._get_pooling_layers(conv_block_input_id,
block_last_layer_input_id)
skip_output_id = conv_block_input_id
for index, layer_id in enumerate(layer_list):
skip_output_id = self.add_layer(
deepcopy(self.layer_list[layer_id]), skip_output_id)
# Add the conv layer
new_relu_layer = StubReLU()
skip_output_id = self.add_layer(new_relu_layer, skip_output_id)
new_conv_layer = StubConv(self.layer_list[start_id].filters,
self.layer_list[end_id].filters, 1)
skip_output_id = self.add_layer(new_conv_layer, skip_output_id)
new_bn_layer = StubBatchNormalization(self.layer_list[end_id].filters)
skip_output_id = self.add_layer(new_bn_layer, skip_output_id)
# Add the add layer.
block_last_layer_output_id = self.adj_list[block_last_layer_input_id][
0][0]
add_input_node_id = self._add_node(
deepcopy(self.node_list[block_last_layer_output_id]))
add_layer = StubAdd()
self._redirect_edge(block_last_layer_input_id,
block_last_layer_output_id, add_input_node_id)
self._add_edge(add_layer, add_input_node_id,
block_last_layer_output_id)
self._add_edge(add_layer, skip_output_id, block_last_layer_output_id)
add_layer.input = [
self.node_list[add_input_node_id], self.node_list[skip_output_id]
]
add_layer.output = self.node_list[block_last_layer_output_id]
self.node_list[
block_last_layer_output_id].shape = add_layer.output_shape
# Set weights to the additional conv layer.
if self.weighted:
filters_end = self.layer_list[end_id].filters
filters_start = self.layer_list[start_id].filters
filter_shape = (1, ) * (
len(self.layer_list[end_id].get_weights()[0].shape) - 2)
weights = np.zeros((filters_end, filters_start) + filter_shape)
bias = np.zeros(filters_end)
new_conv_layer.set_weights((add_noise(weights, np.array([0, 1])),
add_noise(bias, np.array([0, 1]))))
n_filters = filters_end
new_weights = [
add_noise(np.ones(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.zeros(n_filters, dtype=np.float32),
np.array([0, 1])),
add_noise(np.ones(n_filters, dtype=np.float32),
np.array([0, 1]))
]
new_bn_layer.set_weights(new_weights)