Nets.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Python version: 3.6

import torch
from torch import nn
import torch.nn.functional as F
from torchvision import models


class MLP(nn.Module):
    def __init__(self, dim_in, dim_hidden, dim_out):
        super(MLP, self).__init__()
        self.layer_input = nn.Linear(dim_in, 512)
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout()
        self.layer_hidden1 = nn.Linear(512, 256)
        self.layer_hidden2 = nn.Linear(256, 256)
        self.layer_hidden3 = nn.Linear(256, 128)
        self.layer_out = nn.Linear(128, dim_out)
        self.softmax = nn.Softmax(dim=1)
        self.weight_keys = [['layer_input.weight', 'layer_input.bias'],
                            ['layer_hidden1.weight', 'layer_hidden1.bias'],
                            ['layer_hidden2.weight', 'layer_hidden2.bias'],
                            ['layer_hidden3.weight', 'layer_hidden3.bias'],
                            ['layer_out.weight', 'layer_out.bias']
                            ]

    def forward(self, x):
        x = x.view(-1, x.shape[1]*x.shape[-2]*x.shape[-1])
        x = self.layer_input(x)
        x = self.relu(x)

        x = self.layer_hidden1(x)
        x = self.relu(x)

        x = self.layer_hidden2(x)
        x = self.relu(x)

        x = self.layer_hidden3(x)
        x = self.relu(x)

        x = self.layer_out(x)
        return self.softmax(x)


class CNNMnist(nn.Module):
    def __init__(self, args):
        super(CNNMnist, self).__init__()
        self.conv1 = nn.Conv2d(args.num_channels, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, args.num_classes)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, x.shape[1]*x.shape[2]*x.shape[3])
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


class CNNCifar(nn.Module):
    def __init__(self, args):
        super(CNNCifar, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 100)
        self.fc3 = nn.Linear(100, args.num_classes)

        # self.weight_keys = [['fc3.weight', 'fc3.bias'],
        #                     ['fc2.weight', 'fc2.bias'],
        #                     ['fc1.weight', 'fc1.bias'],
        #                     ['conv2.weight', 'conv2.bias'],
        #                     ['conv1.weight', 'conv1.bias'],
        #                     ]

        # self.weight_keys = [['conv1.weight', 'conv1.bias'],
        #                     ['conv2.weight', 'conv2.bias'],
        #                     ['fc2.weight', 'fc2.bias'],
        #                     ['fc3.weight', 'fc3.bias'],
        #                     ['fc1.weight', 'fc1.bias'],
        #                     ]

        self.weight_keys = [['fc1.weight', 'fc1.bias'],
                            ['fc2.weight', 'fc2.bias'],
                            ['fc3.weight', 'fc3.bias'],
                            ['conv2.weight', 'conv2.bias'],
                            ['conv1.weight', 'conv1.bias'],
                            ]

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return F.log_softmax(x, dim=1)