models/jason_cnn.py

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

class CNN_4Layer(nn.Module):
    def __init__(self, in_channels, num_classes, filters=(16,32,64,128), dropout=0.25):
        super(CNN_4Layer, self).__init__()

        self.conv1 = nn.Conv2d(in_channels=in_channels, out_channels=filters[0], kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(in_channels=filters[0], out_channels=filters[1], kernel_size=3, padding=1)
        self.conv3 = nn.Conv2d(in_channels=filters[1], out_channels=filters[2], kernel_size=3, padding=1)
        self.conv4 = nn.Conv2d(in_channels=filters[2], out_channels=filters[3], kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.dropout = nn.Dropout(dropout)
        self.fc1 = nn.Linear(filters[3] * 3 * 3, num_classes)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.pool(x)
        x = self.dropout(x)
        x = F.relu(self.conv2(x))
        x = self.pool(x)
        x = self.dropout(x)
        x = F.relu(self.conv3(x))
        x = self.pool(x)
        x = self.dropout(x)
        x = F.relu(self.conv4(x))
        x = self.pool(x)
        x = self.dropout(x)
        x = x.reshape(x.shape[0], -1)
        x = self.fc1(x)
        return x