From 59e1cf99d0dc5b00e276c72348737f2613f163e5 Mon Sep 17 00:00:00 2001
From: erogol <erogol@hotmail.com>
Date: Wed, 28 Oct 2020 18:30:00 +0100
Subject: [PATCH] config update and ssim implementation

---
 TTS/tts/configs/config.json |  1 +
 TTS/tts/utils/ssim.py       | 75 +++++++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)
 create mode 100644 TTS/tts/utils/ssim.py

diff --git a/TTS/tts/configs/config.json b/TTS/tts/configs/config.json
index 4d3e2674..2cad69c3 100644
--- a/TTS/tts/configs/config.json
+++ b/TTS/tts/configs/config.json
@@ -76,6 +76,7 @@
     "decoder_ssim_alpha": 0.5,     // decoder ssim loss weight. If > 0, it is enabled
     "postnet_ssim_alpha": 0.25,     // postnet ssim loss weight. If > 0, it is enabled
     "ga_alpha": 5.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
+    "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples.
 
 
     // VALIDATION
diff --git a/TTS/tts/utils/ssim.py b/TTS/tts/utils/ssim.py
new file mode 100644
index 00000000..c370f5e5
--- /dev/null
+++ b/TTS/tts/utils/ssim.py
@@ -0,0 +1,75 @@
+# taken from https://github.com/Po-Hsun-Su/pytorch-ssim
+
+import torch
+import torch.nn.functional as F
+from torch.autograd import Variable
+import numpy as np
+from math import exp
+
+def gaussian(window_size, sigma):
+    gauss = torch.Tensor([exp(-(x - window_size//2)**2/float(2*sigma**2)) for x in range(window_size)])
+    return gauss/gauss.sum()
+
+def create_window(window_size, channel):
+    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
+    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
+    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
+    return window
+
+def _ssim(img1, img2, window, window_size, channel, size_average = True):
+    mu1 = F.conv2d(img1, window, padding = window_size//2, groups = channel)
+    mu2 = F.conv2d(img2, window, padding = window_size//2, groups = channel)
+
+    mu1_sq = mu1.pow(2)
+    mu2_sq = mu2.pow(2)
+    mu1_mu2 = mu1*mu2
+
+    sigma1_sq = F.conv2d(img1*img1, window, padding = window_size//2, groups = channel) - mu1_sq
+    sigma2_sq = F.conv2d(img2*img2, window, padding = window_size//2, groups = channel) - mu2_sq
+    sigma12 = F.conv2d(img1*img2, window, padding = window_size//2, groups = channel) - mu1_mu2
+
+    C1 = 0.01**2
+    C2 = 0.03**2
+
+    ssim_map = ((2*mu1_mu2 + C1)*(2*sigma12 + C2))/((mu1_sq + mu2_sq + C1)*(sigma1_sq + sigma2_sq + C2))
+
+    if size_average:
+        return ssim_map.mean()
+    else:
+        return ssim_map.mean(1).mean(1).mean(1)
+
+class SSIM(torch.nn.Module):
+    def __init__(self, window_size = 11, size_average = True):
+        super(SSIM, self).__init__()
+        self.window_size = window_size
+        self.size_average = size_average
+        self.channel = 1
+        self.window = create_window(window_size, self.channel)
+
+    def forward(self, img1, img2):
+        (_, channel, _, _) = img1.size()
+
+        if channel == self.channel and self.window.data.type() == img1.data.type():
+            window = self.window
+        else:
+            window = create_window(self.window_size, channel)
+
+            if img1.is_cuda:
+                window = window.cuda(img1.get_device())
+            window = window.type_as(img1)
+
+            self.window = window
+            self.channel = channel
+
+
+        return _ssim(img1, img2, window, self.window_size, channel, self.size_average)
+
+def ssim(img1, img2, window_size = 11, size_average = True):
+    (_, channel, _, _) = img1.size()
+    window = create_window(window_size, channel)
+
+    if img1.is_cuda:
+        window = window.cuda(img1.get_device())
+    window = window.type_as(img1)
+
+    return _ssim(img1, img2, window, window_size, channel, size_average)
\ No newline at end of file