audio_classifier.py

import torch
import torch.nn as nn
import torch.nn.functional as F

# Le nombre de classes est tiré de ton dataset.
NUM_CLASSES = 2 

class AudioClassifier(nn.Module):
    """
    Réseau de Neurones Convolutionnels (CNN) simple pour la classification audio.
    C'est l'architecture que nous avons entraînée from scratch.
    """
    def __init__(self):
        super(AudioClassifier, self).__init__()
        
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=(5, 5), padding=2)
        self.bn1 = nn.BatchNorm2d(32)
        self.pool1 = nn.MaxPool2d(kernel_size=(2, 2))

        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=(3, 3), padding=1)
        self.bn2 = nn.BatchNorm2d(64)
        self.pool2 = nn.MaxPool2d(kernel_size=(2, 2))

        self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=(3, 3), padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        self.pool3 = nn.MaxPool2d(kernel_size=(2, 2))
        
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))

        self.fc1 = nn.Linear(128 * 1 * 1, NUM_CLASSES) 

    def forward(self, x):
        x = self.pool1(F.relu(self.bn1(self.conv1(x))))
        x = self.pool2(F.relu(self.bn2(self.conv2(x))))
        x = self.pool3(F.relu(self.bn3(self.conv3(x))))
        
        x = self.avgpool(x)
        
        x = torch.flatten(x, 1)

        return self.fc1(x)