towhee
/
torch-vggish
copied
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.
Readme
Files and versions
72 lines
2.1 KiB
72 lines
2.1 KiB
3 years ago
|
# 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.
|
||
|
|
|
||
|
|
import torch
|
||
|
|
import torch.nn as nn
|
||
|
|
import numpy as np
|
||
|
|
import sys
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
sys.path.append(str(Path(__file__).parent))
|
||
|
|
|
||
|
|
import vggish_input
|
||
|
|
|
||
|
|
class Model(nn.Module):
|
||
|
|
"""
|
||
|
|
PyTorch model class
|
||
|
|
"""
|
||
|
|
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)
|
||
|
|
)
|
||
|
|
|
||
|
|
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
|
||
|
|
|
||
|
|
def preprocess(self, audio_path: str):
|
||
|
|
audio_tensors = vggish_input.wavfile_to_examples(audio_path)
|
||
|
|
return audio_tensors
|
||
|
|
|
||
|
|
def train(self):
|
||
|
|
"""
|
||
|
|
For training model
|
||
|
|
"""
|
||
|
|
pass
|