def create_classifier_base(n_input_hops, n_filters, n_hidden_units, kernel_size, pool_size, base_wd=0.001):
# Input
n_mels = localmodule.get_pcen_settings()["top_freq_id"]
tfr_input = keras.layers.Input(shape=(n_mels, n_input_hops, 1), name="tfr_input")
# Layer 1
bn = keras.layers.normalization.BatchNormalization()(tfr_input)
conv1 = keras.layers.Convolution2D(n_filters[0], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv1")(bn)
pool1 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool1")(conv1)
# Layer 2
conv2 = keras.layers.Convolution2D(n_filters[1], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv2")(pool1)
pool2 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool2")(conv2)
# Layer 3
conv3 = keras.layers.Convolution2D(n_filters[2], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv3")(pool2)
# Layer 4
flatten = keras.layers.Flatten()(conv3)
dense1 = keras.layers.Dense(n_hidden_units,
kernel_initializer="he_normal", activation="relu",
kernel_regularizer=keras.regularizers.l2(base_wd),
use_bias=False,
name="dense1")(flatten)
return tfr_input, dense1
def create_hierarchical_baseline_model(n_input_hops, n_filters, n_hidden_units, kernel_size, pool_size, base_wd):
# Input
n_mels = localmodule.get_pcen_settings()["top_freq_id"]
tfr_input = keras.layers.Input(shape=(n_mels, n_input_hops, 1), name="tfr_input")
# Layer 1
bn = keras.layers.normalization.BatchNormalization()(tfr_input)
conv1 = keras.layers.Convolution2D(n_filters[0], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv1")(bn)
pool1 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool1")(conv1)
# Layer 2
conv2 = keras.layers.Convolution2D(n_filters[1], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv2")(pool1)
pool2 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool2")(conv2)
# Layer 3
conv3 = keras.layers.Convolution2D(n_filters[2], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv3")(pool2)
# Layer 4
flattened = keras.layers.Flatten()(conv3)
wd = base_wd / 43.0
y_coarse = keras.layers.Dense(annotations.NUM_MOD_COARSE - 1,
kernel_initializer="normal", activation="sigmoid",
kernel_regularizer=keras.regularizers.l2(wd),
use_bias=False,
name="y_coarse")(flattened)
dense1 = keras.layers.Dense(n_hidden_units,
kernel_initializer="he_normal", activation="relu", use_bias=False,
kernel_regularizer=keras.regularizers.l2(base_wd))(flattened)
wd = base_wd / (43.0 / annotations.NUM_MOD_MEDIUM)
y_medium = keras.layers.Dense(annotations.NUM_MOD_MEDIUM,
kernel_initializer="normal", activation="softmax",
kernel_regularizer=keras.regularizers.l2(wd),
use_bias=False,
name="y_medium")(dense1)
wd = base_wd / (43.0 / annotations.NUM_MOD_FINE)
y_fine = keras.layers.Dense(annotations.NUM_MOD_FINE,
kernel_initializer="normal", activation="softmax",
kernel_regularizer=keras.regularizers.l2(wd),
use_bias=False,
name="y_fine")(dense1)
return [tfr_input], [y_coarse, y_medium, y_fine]
import localmodule
# Define constants.
data_dir = localmodule.get_data_dir()
dataset_name = localmodule.get_dataset_name()
sample_rate = localmodule.get_sample_rate()
args = sys.argv[1:]
aug_str = args[0]
instance_id = int(args[1])
instance_str = str(instance_id)
unit_str = args[2]
if aug_str == "original":
instanced_aug_str = aug_str
else:
instanced_aug_str = "-".join([aug_str, instance_str])
pcen_settings = localmodule.get_pcen_settings()
# Print header.
start_time = int(time.time())
print(str(datetime.datetime.now()) + " Start.")
print("Computing per-channel energy normalization (PCEN) for " +\
dataset_name + " clips, with domain-specific librosa parameters.")
print("Unit: " + unit_str + ".")
print("Augmentation: " + instanced_aug_str + ".")
print("")
print("h5py version: {:s}".format(h5py.__version__))
print("librosa version: {:s}".format(librosa.__version__))
print("")
# Open HDF5 container of waveforms.
hdf5_dataset_name = "_".join([dataset_name, "hdf5"])
def create_hierarchical_containment_model(n_input_hops, n_filters, n_hidden_units, kernel_size, pool_size, base_wd):
# Input
n_mels = localmodule.get_pcen_settings()["top_freq_id"]
tfr_input = keras.layers.Input(shape=(n_mels, n_input_hops, 1), name="tfr_input")
# Layer 1
bn = keras.layers.normalization.BatchNormalization()(tfr_input)
conv1 = keras.layers.Convolution2D(n_filters[0], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv1")(bn)
pool1 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool1")(conv1)
# Layer 2
conv2 = keras.layers.Convolution2D(n_filters[1], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv2")(pool1)
pool2 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool2")(conv2)
# Layer 3
conv3 = keras.layers.Convolution2D(n_filters[2], kernel_size,
padding="same", kernel_initializer="he_normal", activation="relu",
name="conv3")(pool2)
# Layer 4
coarse_layer = keras.layers.Flatten()(conv3)
y_coarse = keras.layers.Lambda(hierarchical_containment_layer_sum_activation, name="y_coarse")(coarse_layer)
# Don't include other
num_medium_classes = len(annotations.MOD_MEDIUM_COUNTS)
medium_children_counts = [0 for _ in range(num_medium_classes)]
for medium_code, medium_count in annotations.MOD_MEDIUM_COUNTS.items():
medium_idx = annotations.MOD_MEDIUM_IDXS[medium_code]
medium_children_counts[medium_idx] = medium_count - 1
med_props = np.array(medium_children_counts) / float(sum(medium_children_counts))
class_sublayer_sizes = partition(n_hidden_units, med_props)
medium_layer = keras.layers.Dense(n_hidden_units,
kernel_initializer="he_normal", activation="relu", use_bias=False,
kernel_regularizer=keras.regularizers.l2(base_wd))(coarse_layer)
medium_nodes = []
fine_sublayers = []
start = 0
for med_idx, (sublayer_size, fine_count) in enumerate(zip(class_sublayer_sizes, medium_children_counts)):
medium_sublayer = keras.layers.Lambda(make_slice_func(int(start), int(start+sublayer_size)), name="medium_sublayer_{}".format(med_idx))(medium_layer)
#
med_node = keras.layers.Lambda(hierarchical_containment_layer_sum_activation)(medium_sublayer)
medium_nodes.append(med_node)
start += sublayer_size
# Make fine layer
wd = base_wd / (43.0 / fine_count)
fine_sublayer = keras.layers.Dense(fine_count, kernel_initializer="he_normal", activation="relu",
use_bias=False, kernel_regularizer=keras.regularizers.l2(wd),
name="fine_sublayer_{}".format(med_idx))(medium_sublayer)
fine_sublayers.append(fine_sublayer)
medium_output = keras.layers.Concatenate()(medium_nodes)
fine_layer = keras.layers.Concatenate()(fine_sublayers)
fine_output = keras.layers.Lambda(K.tanh)(fine_layer)
medium_other_output = keras.layers.Lambda(other_activation)(medium_output)
fine_other_output = keras.layers.Lambda(other_activation)(fine_output)
y_medium = keras.layers.Concatenate(name="y_medium")([medium_output, medium_other_output])
y_fine = keras.layers.Concatenate(name="y_fine")([fine_output, fine_other_output])
return [tfr_input], [y_coarse, y_medium, y_fine]
def create_taxonet_model(n_input_hops, n_filters, n_hidden_units, kernel_size,
pool_size, base_wd):
# Input
n_mels = localmodule.get_pcen_settings()["top_freq_id"]
tfr_input = keras.layers.Input(shape=(n_mels, n_input_hops, 1),
name="tfr_input")
# Layer 1
bn = keras.layers.normalization.BatchNormalization()(tfr_input)
conv1 = keras.layers.Convolution2D(n_filters[0],
kernel_size,
padding="same",
kernel_initializer="he_normal",
activation="relu",
name="conv1")(bn)
pool1 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool1")(conv1)
# Layer 2
conv2 = keras.layers.Convolution2D(n_filters[1],
kernel_size,
padding="same",
kernel_initializer="he_normal",
activation="relu",
name="conv2")(pool1)
pool2 = keras.layers.MaxPooling2D(pool_size=pool_size, name="pool2")(conv2)
# Layer 3
conv3 = keras.layers.Convolution2D(n_filters[2],
kernel_size,
padding="same",
kernel_initializer="he_normal",
activation="relu",
name="conv3")(pool2)
# Layer 4
coarse_layer = keras.layers.Flatten()(conv3)
# why do we divide it by 43 ?
wd = base_wd / 43.0
# single output because coarse layer has only single taxa/class which is
# Passeriforme in the original data
y_coarse = keras.layers.Dense(1,
kernel_initializer="normal",
activation="sigmoid",
kernel_regularizer=keras.regularizers.l2(wd),
use_bias=False,
name="y_coarse")(coarse_layer)
# medium_children_counts: number of sub-taxa in the next layer
# class_sublayer_sizes: number of neurons on the next layer correlated with
# medium_children_counts
# Don't include other
num_medium_classes = len(annotations.MOD_MEDIUM_COUNTS)
medium_children_counts = [0 for _ in range(num_medium_classes)]
for medium_code, medium_count in annotations.MOD_MEDIUM_COUNTS.items():
medium_idx = annotations.MOD_MEDIUM_IDXS[medium_code]
medium_children_counts[medium_idx] = int(medium_count - 1)
# partition neurons correlated with number of childrens of the taxa, (paper
# says this number is only children not grandchildren etc included)
med_props = np.array(medium_children_counts) / float(
sum(medium_children_counts))
class_sublayer_sizes = partition(n_hidden_units, med_props)
# Adjust number of hidden units so that we nicely partition layer in terms of medium classes
# sum(class_sublayer_sizes) should already be equal to the n_hidden_units actually
# just making sure I guess ~?
n_hidden_units = sum(class_sublayer_sizes)
medium_layer = keras.layers.Dense(
n_hidden_units,
kernel_initializer="he_normal",
activation="relu",
use_bias=False,
kernel_regularizer=keras.regularizers.l2(base_wd))(coarse_layer)
medium_nodes = []
fine_sublayers = []
start = 0
for med_idx, (sublayer_size, fine_count) in enumerate(
zip(class_sublayer_sizes, medium_children_counts)):
medium_sublayer = keras.layers.Lambda(
make_slice_func(int(start), int(start + sublayer_size)),
name="medium_sublayer_{}".format(med_idx))(medium_layer)
wd = base_wd / 43.0
med_node = keras.layers.Dense(
1,
kernel_initializer="normal",
activation="sigmoid",
kernel_regularizer=keras.regularizers.l2(wd),
use_bias=False)(medium_sublayer)
medium_nodes.append(med_node)
start += sublayer_size
# Make fine layer
wd = base_wd / (43.0 / fine_count)
fine_sublayer = keras.layers.Dense(
fine_count,
kernel_initializer="he_normal",
activation="sigmoid",
use_bias=False,
kernel_regularizer=keras.regularizers.l2(wd),
name="fine_sublayer_{}".format(med_idx))(medium_sublayer)
fine_sublayers.append(fine_sublayer)
medium_output = keras.layers.Concatenate()(medium_nodes)
fine_output = keras.layers.Concatenate()(fine_sublayers)
medium_other_output = keras.layers.Lambda(other_activation)(medium_output)
fine_other_output = keras.layers.Lambda(other_activation)(fine_output)
y_medium = keras.layers.Concatenate(name="y_medium")(
[medium_output, medium_other_output])
y_fine = keras.layers.Concatenate(name="y_fine")(
[fine_output, fine_other_output])
return [tfr_input], [y_coarse, y_medium, y_fine]