wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-12 12:11:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

ssim loss for tacotron models

Browse Source
This commit is contained in:
erogol
2020-10-28 15:24:18 +01:00
parent 9d0ae2bfb4
commit 9cef923d99
4 changed files with 174 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_layers.py
+70 -1
View File
@@ -2,7 +2,7 @@ import unittest
import torch as T
from TTS.tts.layers.tacotron import Prenet, CBHG, Decoder, Encoder
from TTS.tts.layers.losses import L1LossMasked
from TTS.tts.layers.losses import L1LossMasked, SSIMLoss
from TTS.tts.utils.generic_utils import sequence_mask
# pylint: disable=unused-variable
@@ -149,3 +149,72 @@ class L1LossMaskedTests(unittest.TestCase):
(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())