import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchaudio
import sys

from tqdm import tqdm

class M5(nn.Module):
    def __init__(self, n_input=1, n_output=35, stride=16, n_channel=32):
        super().__init__()
        self.conv1 = nn.Conv1d(n_input, n_channel, kernel_size=80, stride=stride)
        self.bn1 = nn.BatchNorm1d(n_channel)
        self.pool1 = nn.MaxPool1d(4)
        self.conv2 = nn.Conv1d(n_channel, n_channel, kernel_size=3)
        self.bn2 = nn.BatchNorm1d(n_channel)
        self.pool2 = nn.MaxPool1d(4)
        self.conv3 = nn.Conv1d(n_channel, 2 * n_channel, kernel_size=3)
        self.bn3 = nn.BatchNorm1d(2 * n_channel)
        self.pool3 = nn.MaxPool1d(4)
        self.conv4 = nn.Conv1d(2 * n_channel, 2 * n_channel, kernel_size=3)
        self.bn4 = nn.BatchNorm1d(2 * n_channel)
        self.pool4 = nn.MaxPool1d(4)
        self.fc1 = nn.Linear(2 * n_channel, n_output)

        # these need to be different ReLU objects so that they can be individually hooked
        self.act1 = nn.ReLU()
        self.act2 = nn.ReLU()
        self.act3 = nn.ReLU()
        self.act4 = nn.ReLU()

    def forward(self, x):
        x = self.conv1(x)
        x = self.act1(self.bn1(x))
        x = self.pool1(x)
        x = self.conv2(x)
        x = self.act2(self.bn2(x))
        x = self.pool2(x)
        x = self.conv3(x)
        x = self.act3(self.bn3(x))
        x = self.pool3(x)
        x = self.conv4(x)
        x = self.act4(self.bn4(x))
        x = self.pool4(x)
        x = F.avg_pool1d(x, x.shape[-1])
        x = x.permute(0, 2, 1)
        x = self.fc1(x)
        return F.log_softmax(x, dim=2)