mirror of
https://github.com/Anjok07/ultimatevocalremovergui.git
synced 2024-11-27 17:00:59 +01:00
Add files via upload
This commit is contained in:
parent
49e1eb1f65
commit
a78d61493e
113
lib_v5/nets.py
Normal file
113
lib_v5/nets.py
Normal file
@ -0,0 +1,113 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
from lib_v5 import layers
|
||||
from lib_v5 import spec_utils
|
||||
|
||||
|
||||
class BaseASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, nin, ch, dilations=(4, 8, 16)):
|
||||
super(BaseASPPNet, self).__init__()
|
||||
self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
|
||||
self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
|
||||
self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
|
||||
self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
|
||||
|
||||
self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
|
||||
|
||||
self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
|
||||
self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
|
||||
self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
|
||||
self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
|
||||
|
||||
def __call__(self, x):
|
||||
h, e1 = self.enc1(x)
|
||||
h, e2 = self.enc2(h)
|
||||
h, e3 = self.enc3(h)
|
||||
h, e4 = self.enc4(h)
|
||||
|
||||
h = self.aspp(h)
|
||||
|
||||
h = self.dec4(h, e4)
|
||||
h = self.dec3(h, e3)
|
||||
h = self.dec2(h, e2)
|
||||
h = self.dec1(h, e1)
|
||||
|
||||
return h
|
||||
|
||||
|
||||
class CascadedASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, n_fft):
|
||||
super(CascadedASPPNet, self).__init__()
|
||||
self.stg1_low_band_net = BaseASPPNet(2, 16)
|
||||
self.stg1_high_band_net = BaseASPPNet(2, 16)
|
||||
|
||||
self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
|
||||
self.stg2_full_band_net = BaseASPPNet(8, 16)
|
||||
|
||||
self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
|
||||
self.stg3_full_band_net = BaseASPPNet(16, 32)
|
||||
|
||||
self.out = nn.Conv2d(32, 2, 1, bias=False)
|
||||
self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
|
||||
self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
|
||||
|
||||
self.max_bin = n_fft // 2
|
||||
self.output_bin = n_fft // 2 + 1
|
||||
|
||||
self.offset = 128
|
||||
|
||||
def forward(self, x, aggressiveness=None):
|
||||
mix = x.detach()
|
||||
x = x.clone()
|
||||
|
||||
x = x[:, :, :self.max_bin]
|
||||
|
||||
bandw = x.size()[2] // 2
|
||||
aux1 = torch.cat([
|
||||
self.stg1_low_band_net(x[:, :, :bandw]),
|
||||
self.stg1_high_band_net(x[:, :, bandw:])
|
||||
], dim=2)
|
||||
|
||||
h = torch.cat([x, aux1], dim=1)
|
||||
aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
|
||||
|
||||
h = torch.cat([x, aux1, aux2], dim=1)
|
||||
h = self.stg3_full_band_net(self.stg3_bridge(h))
|
||||
|
||||
mask = torch.sigmoid(self.out(h))
|
||||
mask = F.pad(
|
||||
input=mask,
|
||||
pad=(0, 0, 0, self.output_bin - mask.size()[2]),
|
||||
mode='replicate')
|
||||
|
||||
if self.training:
|
||||
aux1 = torch.sigmoid(self.aux1_out(aux1))
|
||||
aux1 = F.pad(
|
||||
input=aux1,
|
||||
pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
|
||||
mode='replicate')
|
||||
aux2 = torch.sigmoid(self.aux2_out(aux2))
|
||||
aux2 = F.pad(
|
||||
input=aux2,
|
||||
pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
|
||||
mode='replicate')
|
||||
return mask * mix, aux1 * mix, aux2 * mix
|
||||
else:
|
||||
if aggressiveness:
|
||||
mask[:, :, :aggressiveness['split_bin']] = torch.pow(mask[:, :, :aggressiveness['split_bin']], 1 + aggressiveness['value'] / 3)
|
||||
mask[:, :, aggressiveness['split_bin']:] = torch.pow(mask[:, :, aggressiveness['split_bin']:], 1 + aggressiveness['value'])
|
||||
|
||||
return mask * mix
|
||||
|
||||
def predict(self, x_mag, aggressiveness=None):
|
||||
h = self.forward(x_mag, aggressiveness)
|
||||
|
||||
if self.offset > 0:
|
||||
h = h[:, :, :, self.offset:-self.offset]
|
||||
assert h.size()[3] > 0
|
||||
|
||||
return h
|
112
lib_v5/nets_33966KB.py
Normal file
112
lib_v5/nets_33966KB.py
Normal file
@ -0,0 +1,112 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
from lib_v5 import layers_33966KB as layers
|
||||
|
||||
|
||||
class BaseASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, nin, ch, dilations=(4, 8, 16, 32)):
|
||||
super(BaseASPPNet, self).__init__()
|
||||
self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
|
||||
self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
|
||||
self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
|
||||
self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
|
||||
|
||||
self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
|
||||
|
||||
self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
|
||||
self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
|
||||
self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
|
||||
self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
|
||||
|
||||
def __call__(self, x):
|
||||
h, e1 = self.enc1(x)
|
||||
h, e2 = self.enc2(h)
|
||||
h, e3 = self.enc3(h)
|
||||
h, e4 = self.enc4(h)
|
||||
|
||||
h = self.aspp(h)
|
||||
|
||||
h = self.dec4(h, e4)
|
||||
h = self.dec3(h, e3)
|
||||
h = self.dec2(h, e2)
|
||||
h = self.dec1(h, e1)
|
||||
|
||||
return h
|
||||
|
||||
|
||||
class CascadedASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, n_fft):
|
||||
super(CascadedASPPNet, self).__init__()
|
||||
self.stg1_low_band_net = BaseASPPNet(2, 16)
|
||||
self.stg1_high_band_net = BaseASPPNet(2, 16)
|
||||
|
||||
self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
|
||||
self.stg2_full_band_net = BaseASPPNet(8, 16)
|
||||
|
||||
self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
|
||||
self.stg3_full_band_net = BaseASPPNet(16, 32)
|
||||
|
||||
self.out = nn.Conv2d(32, 2, 1, bias=False)
|
||||
self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
|
||||
self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
|
||||
|
||||
self.max_bin = n_fft // 2
|
||||
self.output_bin = n_fft // 2 + 1
|
||||
|
||||
self.offset = 128
|
||||
|
||||
def forward(self, x, aggressiveness=None):
|
||||
mix = x.detach()
|
||||
x = x.clone()
|
||||
|
||||
x = x[:, :, :self.max_bin]
|
||||
|
||||
bandw = x.size()[2] // 2
|
||||
aux1 = torch.cat([
|
||||
self.stg1_low_band_net(x[:, :, :bandw]),
|
||||
self.stg1_high_band_net(x[:, :, bandw:])
|
||||
], dim=2)
|
||||
|
||||
h = torch.cat([x, aux1], dim=1)
|
||||
aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
|
||||
|
||||
h = torch.cat([x, aux1, aux2], dim=1)
|
||||
h = self.stg3_full_band_net(self.stg3_bridge(h))
|
||||
|
||||
mask = torch.sigmoid(self.out(h))
|
||||
mask = F.pad(
|
||||
input=mask,
|
||||
pad=(0, 0, 0, self.output_bin - mask.size()[2]),
|
||||
mode='replicate')
|
||||
|
||||
if self.training:
|
||||
aux1 = torch.sigmoid(self.aux1_out(aux1))
|
||||
aux1 = F.pad(
|
||||
input=aux1,
|
||||
pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
|
||||
mode='replicate')
|
||||
aux2 = torch.sigmoid(self.aux2_out(aux2))
|
||||
aux2 = F.pad(
|
||||
input=aux2,
|
||||
pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
|
||||
mode='replicate')
|
||||
return mask * mix, aux1 * mix, aux2 * mix
|
||||
else:
|
||||
if aggressiveness:
|
||||
mask[:, :, :aggressiveness['split_bin']] = torch.pow(mask[:, :, :aggressiveness['split_bin']], 1 + aggressiveness['value'] / 3)
|
||||
mask[:, :, aggressiveness['split_bin']:] = torch.pow(mask[:, :, aggressiveness['split_bin']:], 1 + aggressiveness['value'])
|
||||
|
||||
return mask * mix
|
||||
|
||||
def predict(self, x_mag, aggressiveness=None):
|
||||
h = self.forward(x_mag, aggressiveness)
|
||||
|
||||
if self.offset > 0:
|
||||
h = h[:, :, :, self.offset:-self.offset]
|
||||
assert h.size()[3] > 0
|
||||
|
||||
return h
|
113
lib_v5/nets_537227KB.py
Normal file
113
lib_v5/nets_537227KB.py
Normal file
@ -0,0 +1,113 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
from torch import nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
from lib_v5 import layers_537238KB as layers
|
||||
|
||||
|
||||
class BaseASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, nin, ch, dilations=(4, 8, 16)):
|
||||
super(BaseASPPNet, self).__init__()
|
||||
self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
|
||||
self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
|
||||
self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
|
||||
self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
|
||||
|
||||
self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
|
||||
|
||||
self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
|
||||
self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
|
||||
self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
|
||||
self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
|
||||
|
||||
def __call__(self, x):
|
||||
h, e1 = self.enc1(x)
|
||||
h, e2 = self.enc2(h)
|
||||
h, e3 = self.enc3(h)
|
||||
h, e4 = self.enc4(h)
|
||||
|
||||
h = self.aspp(h)
|
||||
|
||||
h = self.dec4(h, e4)
|
||||
h = self.dec3(h, e3)
|
||||
h = self.dec2(h, e2)
|
||||
h = self.dec1(h, e1)
|
||||
|
||||
return h
|
||||
|
||||
|
||||
class CascadedASPPNet(nn.Module):
|
||||
|
||||
def __init__(self, n_fft):
|
||||
super(CascadedASPPNet, self).__init__()
|
||||
self.stg1_low_band_net = BaseASPPNet(2, 64)
|
||||
self.stg1_high_band_net = BaseASPPNet(2, 64)
|
||||
|
||||
self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
|
||||
self.stg2_full_band_net = BaseASPPNet(32, 64)
|
||||
|
||||
self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
|
||||
self.stg3_full_band_net = BaseASPPNet(64, 128)
|
||||
|
||||
self.out = nn.Conv2d(128, 2, 1, bias=False)
|
||||
self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
|
||||
self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
|
||||
|
||||
self.max_bin = n_fft // 2
|
||||
self.output_bin = n_fft // 2 + 1
|
||||
|
||||
self.offset = 128
|
||||
|
||||
def forward(self, x, aggressiveness=None):
|
||||
mix = x.detach()
|
||||
x = x.clone()
|
||||
|
||||
x = x[:, :, :self.max_bin]
|
||||
|
||||
bandw = x.size()[2] // 2
|
||||
aux1 = torch.cat([
|
||||
self.stg1_low_band_net(x[:, :, :bandw]),
|
||||
self.stg1_high_band_net(x[:, :, bandw:])
|
||||
], dim=2)
|
||||
|
||||
h = torch.cat([x, aux1], dim=1)
|
||||
aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
|
||||
|
||||
h = torch.cat([x, aux1, aux2], dim=1)
|
||||
h = self.stg3_full_band_net(self.stg3_bridge(h))
|
||||
|
||||
mask = torch.sigmoid(self.out(h))
|
||||
mask = F.pad(
|
||||
input=mask,
|
||||
pad=(0, 0, 0, self.output_bin - mask.size()[2]),
|
||||
mode='replicate')
|
||||
|
||||
if self.training:
|
||||
aux1 = torch.sigmoid(self.aux1_out(aux1))
|
||||
aux1 = F.pad(
|
||||
input=aux1,
|
||||
pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
|
||||
mode='replicate')
|
||||
aux2 = torch.sigmoid(self.aux2_out(aux2))
|
||||
aux2 = F.pad(
|
||||
input=aux2,
|
||||
pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
|
||||
mode='replicate')
|
||||
return mask * mix, aux1 * mix, aux2 * mix
|
||||
else:
|
||||
if aggressiveness:
|
||||
mask[:, :, :aggressiveness['split_bin']] = torch.pow(mask[:, :, :aggressiveness['split_bin']], 1 + aggressiveness['value'] / 3)
|
||||
mask[:, :, aggressiveness['split_bin']:] = torch.pow(mask[:, :, aggressiveness['split_bin']:], 1 + aggressiveness['value'])
|
||||
|
||||
return mask * mix
|
||||
|
||||
def predict(self, x_mag, aggressiveness=None):
|
||||
h = self.forward(x_mag, aggressiveness)
|
||||
|
||||
if self.offset > 0:
|
||||
h = h[:, :, :, self.offset:-self.offset]
|
||||
assert h.size()[3] > 0
|
||||
|
||||
return h
|
@ -369,6 +369,23 @@ def ensembling(a, specs):
|
||||
|
||||
return spec
|
||||
|
||||
def stft(wave, nfft, hl):
|
||||
wave_left = np.asfortranarray(wave[0])
|
||||
wave_right = np.asfortranarray(wave[1])
|
||||
spec_left = librosa.stft(wave_left, nfft, hop_length=hl)
|
||||
spec_right = librosa.stft(wave_right, nfft, hop_length=hl)
|
||||
spec = np.asfortranarray([spec_left, spec_right])
|
||||
|
||||
return spec
|
||||
|
||||
def istft(spec, hl):
|
||||
spec_left = np.asfortranarray(spec[0])
|
||||
spec_right = np.asfortranarray(spec[1])
|
||||
|
||||
wave_left = librosa.istft(spec_left, hop_length=hl)
|
||||
wave_right = librosa.istft(spec_right, hop_length=hl)
|
||||
wave = np.asfortranarray([wave_left, wave_right])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import cv2
|
||||
|
Loading…
Reference in New Issue
Block a user