File size: 8,598 Bytes
2493d72 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
import unittest
import torch as T
from TTS.tts.layers.tacotron import Prenet, CBHG, Decoder, Encoder
from TTS.tts.layers.losses import L1LossMasked, SSIMLoss
from TTS.tts.utils.generic_utils import sequence_mask
# pylint: disable=unused-variable
class PrenetTests(unittest.TestCase):
def test_in_out(self): #pylint: disable=no-self-use
layer = Prenet(128, out_features=[256, 128])
dummy_input = T.rand(4, 128)
print(layer)
output = layer(dummy_input)
assert output.shape[0] == 4
assert output.shape[1] == 128
class CBHGTests(unittest.TestCase):
def test_in_out(self):
#pylint: disable=attribute-defined-outside-init
layer = self.cbhg = CBHG(
128,
K=8,
conv_bank_features=80,
conv_projections=[160, 128],
highway_features=80,
gru_features=80,
num_highways=4)
# B x D x T
dummy_input = T.rand(4, 128, 8)
print(layer)
output = layer(dummy_input)
assert output.shape[0] == 4
assert output.shape[1] == 8
assert output.shape[2] == 160
class DecoderTests(unittest.TestCase):
@staticmethod
def test_in_out():
layer = Decoder(
in_channels=256,
frame_channels=80,
r=2,
memory_size=4,
attn_windowing=False,
attn_norm="sigmoid",
attn_K=5,
attn_type="original",
prenet_type='original',
prenet_dropout=True,
forward_attn=True,
trans_agent=True,
forward_attn_mask=True,
location_attn=True,
separate_stopnet=True)
dummy_input = T.rand(4, 8, 256)
dummy_memory = T.rand(4, 2, 80)
output, alignment, stop_tokens = layer(
dummy_input, dummy_memory, mask=None)
assert output.shape[0] == 4
assert output.shape[1] == 80, "size not {}".format(output.shape[1])
assert output.shape[2] == 2, "size not {}".format(output.shape[2])
assert stop_tokens.shape[0] == 4
class EncoderTests(unittest.TestCase):
def test_in_out(self): #pylint: disable=no-self-use
layer = Encoder(128)
dummy_input = T.rand(4, 8, 128)
print(layer)
output = layer(dummy_input)
print(output.shape)
assert output.shape[0] == 4
assert output.shape[1] == 8
assert output.shape[2] == 256 # 128 * 2 BiRNN
class L1LossMaskedTests(unittest.TestCase):
def test_in_out(self): #pylint: disable=no-self-use
# test input == target
layer = L1LossMasked(seq_len_norm=False)
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.ones(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 0.0
# test input != target
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 1.0, "1.0 vs {}".format(output.item())
# test if padded values of input makes any difference
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert output.item() == 1.0, "1.0 vs {}".format(output.item())
dummy_input = T.rand(4, 8, 128).float()
dummy_target = dummy_input.detach()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert output.item() == 0, "0 vs {}".format(output.item())
# seq_len_norm = True
# test input == target
layer = L1LossMasked(seq_len_norm=True)
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.ones(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 0.0
# test input != target
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 1.0, "1.0 vs {}".format(output.item())
# test if padded values of input makes any difference
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert abs(output.item() - 1.0) < 1e-5, "1.0 vs {}".format(output.item())
dummy_input = T.rand(4, 8, 128).float()
dummy_target = dummy_input.detach()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert output.item() == 0, "0 vs {}".format(output.item())
class SSIMLossTests(unittest.TestCase):
def test_in_out(self): #pylint: disable=no-self-use
# test input == target
layer = SSIMLoss()
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.ones(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 0.0
# test input != target
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert abs(output.item() - 1.0) < 1e-4 , "1.0 vs {}".format(output.item())
# test if padded values of input makes any difference
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert abs(output.item() - 1.0) < 1e-4, "1.0 vs {}".format(output.item())
dummy_input = T.rand(4, 8, 128).float()
dummy_target = dummy_input.detach()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert output.item() == 0, "0 vs {}".format(output.item())
# seq_len_norm = True
# test input == target
layer = L1LossMasked(seq_len_norm=True)
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.ones(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 0.0
# test input != target
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.ones(4) * 8).long()
output = layer(dummy_input, dummy_target, dummy_length)
assert output.item() == 1.0, "1.0 vs {}".format(output.item())
# test if padded values of input makes any difference
dummy_input = T.ones(4, 8, 128).float()
dummy_target = T.zeros(4, 8, 128).float()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert abs(output.item() - 1.0) < 1e-5, "1.0 vs {}".format(output.item())
dummy_input = T.rand(4, 8, 128).float()
dummy_target = dummy_input.detach()
dummy_length = (T.arange(5, 9)).long()
mask = (
(sequence_mask(dummy_length).float() - 1.0) * 100.0).unsqueeze(2)
output = layer(dummy_input + mask, dummy_target, dummy_length)
assert output.item() == 0, "0 vs {}".format(output.item())
|