-
Notifications
You must be signed in to change notification settings - Fork 388
/
snr.py
65 lines (52 loc) · 2.18 KB
/
snr.py
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
# Copyright The PyTorch Lightning team.
#
# 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.
import torch
from torch import Tensor
from torchmetrics.utilities.checks import _check_same_shape
def snr(preds: Tensor, target: Tensor, zero_mean: bool = False) -> Tensor:
r""" `Signal-to-noise ratio (SNR) <https://en.wikipedia.org/wiki/Signal-to-noise_ratio>`_:
.. math::
\text{SNR} = \frac{P_{signal}}{P_{noise}}
where :math:`P` denotes the power of each signal. The SNR metric compares the level
of the desired signal to the level of background noise. Therefore, a high value of
SNR means that the audio is clear.
Args:
preds:
shape ``[...,time]``
target:
shape ``[...,time]``
zero_mean:
if to zero mean target and preds or not
Returns:
snr value of shape [...]
Example:
>>> from torchmetrics.functional.audio import snr
>>> target = torch.tensor([3.0, -0.5, 2.0, 7.0])
>>> preds = torch.tensor([2.5, 0.0, 2.0, 8.0])
>>> snr_val = snr(preds, target)
>>> snr_val
tensor(16.1805)
References:
[1] Le Roux, Jonathan, et al. "SDR half-baked or well done." IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP) 2019.
"""
_check_same_shape(preds, target)
EPS = torch.finfo(preds.dtype).eps
if zero_mean:
target = target - torch.mean(target, dim=-1, keepdim=True)
preds = preds - torch.mean(preds, dim=-1, keepdim=True)
noise = target - preds
snr_value = (torch.sum(target**2, dim=-1) + EPS) / (torch.sum(noise**2, dim=-1) + EPS)
snr_value = 10 * torch.log10(snr_value)
return snr_value