17. Generative Adversarial Network#
GAN，敵対的生成ネットワーク[Goodfellow et al., 2014]
Show code cell source
# packageのimport
from typing import Any, Union, Callable, Type, TypeVar
from tqdm.std import trange,tqdm
import numpy as np
import numpy.typing as npt
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
import seaborn as sns
from PIL import Image
import cv2
import requests
# pytorch関連のimport
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from src import utils
SEED = 2023_7_17
utils.set_seed(SEED)
17.1. GANの仕組み#
17.1.1. 贋作者と鑑定士#
17.1.1.1. Generator (贋作者)#
17.1.1.2. Discriminator (鑑定士)#
17.1.2. 損失関数#
17.1.3. 訓練の流れ#
17.1.4. 実験#
17.1.4.1. 実験結果#
17.2. 参考文献#
17.2.1. 論文等#
- GPAM+14
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In Z Ghahramani, M Welling, C Cortes, N Lawrence, and K Q Weinberger, editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014.