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.audio.timit_data_provider import TIMITDataProvider 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 "../" TIMIT_lst = TIMITDataProvider.load_speaker_list( ds_dir + 'datasets/TIMIT/traininglist_100/testlist_400.txt') dp = TIMITDataProvider( # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", min_cluster_count=1, max_cluster_count=15, return_1d_audio_data=False, test_classes=TIMIT_lst[:200], validate_classes=TIMIT_lst[200:], concat_audio_files_of_speaker=True, # Create at least two 1s snippets per speaker and create also some hints window_width=[(100, 100), (200, 200), (300, 300), (400, 400)], minimum_snippets_per_cluster=[(100, 100), (100, 100)], split_audio_pieces_longer_than_and_create_hints=100)
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.audio.timit_data_provider import TIMITDataProvider 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 "../" TIMIT_lst = TIMITDataProvider.load_speaker_list( ds_dir + 'datasets/TIMIT/traininglist_100/testlist_20.txt') dp = TIMITDataProvider( # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", min_cluster_count=1, max_cluster_count=5, return_1d_audio_data=False, test_classes=TIMIT_lst, validate_classes=TIMIT_lst, concat_audio_files_of_speaker=True) en = CnnEmbedding(output_size=256, cnn_layers_per_block=1, block_feature_counts=[32, 64], fc_layer_feature_counts=[], hidden_activation=LeakyReLU(),
# found, but some of them may be empty from sys import platform from impl.data.audio.timit_data_provider import TIMITDataProvider from impl.data.image.facescrub_data_provider import FaceScrubDataProvider 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_gpulab/" if is_linux else "G:/tmp/" ds_dir = "./" if is_linux else "../" rnd = Random() rnd.seed(1729) TIMIT_lst = TIMITDataProvider.load_speaker_list( 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 = FaceScrubDataProvider( top_dir + '/facescrub_128x128', min_cluster_count=1,
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.mnist_data_provider import MNISTDataProvider from impl.data.audio.timit_data_provider import TIMITDataProvider 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 "../" speaker_list = TIMITDataProvider.load_speaker_list(ds_dir + 'datasets/TIMIT/traininglist_100/testlist_20.txt')[:10] dp = TIMITDataProvider( # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", min_cluster_count=10, max_cluster_count=10, return_1d_audio_data=False, train_classes=speaker_list, test_classes=speaker_list, validate_classes=speaker_list, concat_audio_files_of_speaker=True ) en = CnnEmbedding(
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.audio.timit_data_provider import TIMITDataProvider 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 "../" TIMIT_lst = TIMITDataProvider.load_speaker_list(ds_dir + 'datasets/TIMIT/traininglist_100/testlist_200.txt') # Shuffle the speakers random.seed(1) random.shuffle(TIMIT_lst) # Only use the first 20 speakers TIMIT_lst = TIMIT_lst[:20] dp = TIMITDataProvider( data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", return_1d_audio_data=False, train_classes=TIMIT_lst, test_classes=TIMIT_lst,
from impl.data.audio.timit_data_provider import TIMITDataProvider 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/" TIMIT20_lst = [ 'MTDB0', 'FCMG0', 'MABW0', 'MWEM0', 'MTLS0', 'MMAM0', 'MTJU0', 'FECD0', 'FVMH0', 'MDCD0', 'MJPG0', 'MRSP0', 'MRFK0', 'FCAU0', 'MRCG0', 'MRKM0', 'MPRT0', 'MCTT0', 'FEME0', 'MCRE0' ] dp = TIMITDataProvider( # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", min_cluster_count=1, max_cluster_count=5, return_1d_audio_data=False, test_classes=TIMIT20_lst, validate_classes=TIMIT20_lst, concat_audio_files_of_speaker=True) en = CnnEmbedding(output_size=32, cnn_layers_per_block=1, block_feature_counts=[32, 64], fc_layer_feature_counts=[], hidden_activation=LeakyReLU(), final_activation='tanh', batch_norm_for_init_layer=True) c_nn = ClusterNNTry00_V16(dp, 20, en,
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.audio.timit_data_provider import TIMITDataProvider 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 "../" TIMIT_lst = TIMITDataProvider.load_speaker_list( ds_dir + 'datasets/TIMIT/traininglist_100/testlist_200.txt') dp = TIMITDataProvider( # data_dir=top_dir + "/test/TIMIT_mini", cache_directory=top_dir + "/test/cache", data_dir=top_dir + "/TIMIT", cache_directory=top_dir + "/test/cache", min_cluster_count=1, max_cluster_count=5, return_1d_audio_data=True, test_classes=TIMIT_lst, validate_classes=TIMIT_lst, concat_audio_files_of_speaker=True, minimum_snippets_per_cluster=[(200, 200), (100, 100)], window_width=[(100, 200)]) en = CnnEmbedding(output_size=256, cnn_layers_per_block=1, block_feature_counts=[64, 128, 256],