VGG16 pre-trainedの中間層を用いたモデル構築例[pytorch]

6月 21, 20207月 25, 2020

import os
import glob
import random
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
import json
from PIL import Image
from tqdm import tqdm
import matplotlib.pyplot as plt
# get_ipython().run_line_magic('matplotlib', 'inline')

import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data as data
import torchvision
from torchvision import models, transforms

torch.manual_seed(1234)
np.random.seed(1234)
random.seed(1234)

# VGG16の中間層を抽出することでモデルを構築
class custom_VGG16(nn.Module):
    def __init__(self):
        super(custom_VGG16, self).__init__()
        
        # 22層それぞれから特徴を抽出
        features = list(models.vgg16(pretrained=True).features)[:23]
        self.features = nn.ModuleList(features).eval()
        
    def forward(self, x):
        # 22層目から特徴抽出
        model = self.features[22]
        x = model(x)
        x = nn.Linear(512 * 7 * 7, 4096)(x)
        x = nn.ReLU(True)(x)
        x = nn.Dropout()(x)
        x = nn.Linear(4096, 4096)(x)
        x = nn.ReLU(True)(x)
        x = nn.Dropout()(x)
        x = nn.Linear(4096, 2)
        
        return x
        
def main():
    model = custom_VGG16()
    print(model)
    input = torch.randn(32, 3, 224, 224)
    out = model(input)
    print(type(out))
    for x in out:
        print(x.size(), type(x))
        
if __name__ == "__main__":
    use_pretrained = True
    net = models.vgg16(pretrained=use_pretrained)
    
    print(net)

>>>

VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace=True)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace=True)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace=True)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace=True)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace=True)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace=True)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace=True)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace=True)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace=True)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace=True)
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)