| import torch | |
| import torch.nn as nn | |
| class DeepMLP(nn.Module): | |
| """Model 3: Głęboka sieć z progresywnym Dropout i L2""" | |
| def __init__(self): | |
| super(DeepMLP, self).__init__() | |
| self.fc1 = nn.Linear(5000, 1024) | |
| self.bn1 = nn.BatchNorm1d(1024) | |
| self.dropout1 = nn.Dropout(0.5) | |
| self.fc2 = nn.Linear(1024, 512) | |
| self.bn2 = nn.BatchNorm1d(512) | |
| self.dropout2 = nn.Dropout(0.4) | |
| self.fc3 = nn.Linear(512, 256) | |
| self.bn3 = nn.BatchNorm1d(256) | |
| self.dropout3 = nn.Dropout(0.3) | |
| self.fc4 = nn.Linear(256, 128) | |
| self.bn4 = nn.BatchNorm1d(128) | |
| self.dropout4 = nn.Dropout(0.2) | |
| self.fc5 = nn.Linear(128, 6) | |
| self.relu = nn.ReLU() | |
| def forward(self, x): | |
| x = self.relu(self.bn1(self.fc1(x))) | |
| x = self.dropout1(x) | |
| x = self.relu(self.bn2(self.fc2(x))) | |
| x = self.dropout2(x) | |
| x = self.relu(self.bn3(self.fc3(x))) | |
| x = self.dropout3(x) | |
| x = self.relu(self.bn4(self.fc4(x))) | |
| x = self.dropout4(x) | |
| x = self.fc5(x) | |
| return x | |