ds_dir + 'datasets/TIMIT/traininglist_100/testlist_200.txt')
rnd.shuffle(TIMIT_lst)
p = Augmentor.Pipeline()
p.random_distortion(probability=1,
grid_width=4,
grid_height=4,
magnitude=8)
p.flip_left_right(probability=0.5)
p.flip_top_bottom(probability=0.5)
p.rotate90(probability=0.5)
p.rotate270(probability=0.5)
dp = Birds200DataProvider(
min_cluster_count=1,
max_cluster_count=5,
target_img_size=(128, 128),
min_element_count_per_cluster=2,
additional_augmentor=lambda x: p.sample_with_array(x))
dp.use_augmentation_for_test_data = False
dp.use_augmentation_for_validation_data = False
en = CnnEmbedding(output_size=256,
cnn_layers_per_block=1,
block_feature_counts=[32, 64, 128],
fc_layer_feature_counts=[256],
hidden_activation=LeakyReLU(),
final_activation=LeakyReLU(),
batch_norm_for_init_layer=False,
batch_norm_after_activation=True,
batch_norm_for_final_layer=True,
dropout_init=0.25,
dropout_after_max_pooling=[0.25, 0.25, 0.25],
from impl.nn.base.embedding_nn.cnn_embedding import CnnEmbedding
is_linux = platform == "linux" or platform == "linux2"
top_dir = "/cluster/home/meierbe8/data/MT/" if is_linux else "G:/tmp/"
ds_dir = "./" if is_linux else "../"
p = Augmentor.Pipeline()
p.random_distortion(probability=1, grid_width=4, grid_height=4, magnitude=8)
p.flip_left_right(probability=0.5)
p.flip_top_bottom(probability=0.5)
p.rotate90(probability=0.5)
p.rotate270(probability=0.5)
dp = Birds200DataProvider(
min_cluster_count=1,
max_cluster_count=5,
additional_augmentor=lambda x: p.sample_with_array(x),
target_img_size=(96, 96)
)
en = CnnEmbedding(
output_size=2,
cnn_layers_per_block=2, block_feature_counts=[2],
fc_layer_feature_counts=[2], hidden_activation=LeakyReLU(), final_activation=LeakyReLU(),
batch_norm_for_init_layer=False, batch_norm_after_activation=True, batch_norm_for_final_layer=True,
)
c_nn = ClusterNNTry00_V30(dp, 5, en, lstm_layers=1, internal_embedding_size=3, cluster_count_dense_layers=1, cluster_count_dense_units=2,
output_dense_layers=1, output_dense_units=2, cluster_count_lstm_layers=2, cluster_count_lstm_units=2,
kl_embedding_size=2)
c_nn.include_self_comparison = False
c_nn.weighted_classes = True
if __name__ == '__main__':
# Difference to test_cluster_nn_try00.py: No embedding is used and the network always returns that 10 clusters were
# found, but some of them may be empty
from sys import platform
from impl.data.image.birds200_data_provider import Birds200DataProvider
from impl.nn.base.embedding_nn.cnn_embedding import CnnEmbedding
is_linux = platform == "linux" or platform == "linux2"
top_dir = "/cluster/home/meierbe8/data/MT/" if is_linux else "G:/tmp/"
ds_dir = "./" if is_linux else "../"
dp = Birds200DataProvider(min_cluster_count=1, max_cluster_count=5)
en = CnnEmbedding(output_size=256,
cnn_layers_per_block=1,
block_feature_counts=[64, 128, 256],
fc_layer_feature_counts=[256],
hidden_activation=LeakyReLU(),
final_activation=LeakyReLU(),
batch_norm_for_init_layer=False,
batch_norm_after_activation=True,
batch_norm_for_final_layer=True,
dropout_after_fc=[0.5],
dropout_after_max_pooling=[0.5, 0.5, 0.5],
dropout_init=0.5)
c_nn = ClusterNNTry00_V50(dp,
20,
# data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache",
# min_cluster_count=5,
# max_cluster_count=5,
# return_1d_audio_data=False,
#
# train_classes=speaker_list,
# test_classes=speaker_list,
# validate_classes=speaker_list,
#
# concat_audio_files_of_speaker=True
# )
classes = list(range(5))
dp = Birds200DataProvider(
train_classes=classes,
validate_classes=classes,
test_classes=classes,
min_cluster_count=5,
max_cluster_count=5,
)
def get_cnn(dataprovider=None):
if dataprovider is None:
dataprovider = dp
en = CnnEmbedding(output_size=100,
cnn_layers_per_block=1,
block_feature_counts=[32, 64],
fc_layer_feature_counts=[100],
hidden_activation='relu',
final_activation='relu',
batch_norm_for_init_layer=True,
dropout_after_max_pooling=0.5,