# VGGish is an auido embedding model developed by Tensorflow:
# https://github.com/tensorflow/models/tree/master/research/audioset/vggish
#
# Pytorch implementation is adapted from: https://github.com/harritaylor/torch-vggish
#
# All modifications are made by / Copyright 2021 Zilliz. 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 torch import nn
[docs]class VGG(nn.Module):
"""
PyTorch model class
"""
[docs] def __init__(self):
super().__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 64, 3, 1, 1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
nn.Conv2d(64, 128, 3, 1, 1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
nn.Conv2d(128, 256, 3, 1, 1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 256, 3, 1, 1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
nn.Conv2d(256, 512, 3, 1, 1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, 3, 1, 1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2))
self.embeddings = nn.Sequential(
nn.Linear(512 * 24, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, 128),
#nn.ReLU(inplace=True)
)
[docs] def forward(self, x):
x = self.features(x).permute(0, 2, 3, 1).contiguous()
x = x.view(x.size(0), -1)
x = self.embeddings(x)
return x