You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/paddlespeech/t2s/modules/ssim.py

81 lines
2.7 KiB

# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from math import exp
import paddle
import paddle.nn.functional as F
from paddle import nn
def gaussian(window_size, sigma):
gauss = paddle.to_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 = paddle.matmul(_1D_window, paddle.transpose(
_1D_window, [1, 0])).unsqueeze([0, 1])
window = paddle.expand(_2D_window, [channel, 1, window_size, window_size])
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(nn.Layer):
def __init__(self, window_size=11, size_average=True):
super().__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):
return _ssim(img1, img2, self.window, self.window_size, self.channel,
self.size_average)
def ssim(img1, img2, window_size=11, size_average=True):
(_, channel, _, _) = img1.shape
window = create_window(window_size, channel)
return _ssim(img1, img2, window, window_size, channel, size_average)