電子發(fā)燒友網(wǎng)>電子資料下載>電子資料>PyTorch教程20.2之深度卷積生成對抗網(wǎng)絡(luò)

PyTorch教程20.2之深度卷積生成對抗網(wǎng)絡(luò)

2076562 2023-06-05 | pdf | 0.29 MB | 次下載 | 2積分

資料介紹

在20.1 節(jié)中，我們介紹了 GAN 工作原理背后的基本思想。我們展示了他們可以從一些簡單的、易于采樣的分布中抽取樣本，比如均勻分布或正態(tài)分布，并將它們轉(zhuǎn)換成看起來與某些數(shù)據(jù)集的分布相匹配的樣本。雖然我們匹配 2D 高斯分布的示例說明了要點，但它并不是特別令人興奮。

在本節(jié)中，我們將演示如何使用 GAN 生成逼真的圖像。我們的模型將基于 Radford等人介紹的深度卷積 GAN (DCGAN)。（2015 年）。我們將借用已經(jīng)證明在判別計算機(jī)視覺問題上非常成功的卷積架構(gòu)，并展示如何通過 GAN 來利用它們來生成逼真的圖像。

						import warnings
import torch
import torchvision
from torch import nn
from d2l import torch as d2l

						 

						from mxnet import gluon, init, np, npx
from mxnet.gluon import nn
from d2l import mxnet as d2l

npx.set_np()

						import tensorflow as tf
from d2l import tensorflow as d2l

20.2.1。口袋妖怪?jǐn)?shù)據(jù)集

我們將使用的數(shù)據(jù)集是從pokemondb獲得的 Pokemon 精靈的集合。首先下載、提取和加載此數(shù)據(jù)集。

							#@save
d2l.DATA_HUB['pokemon'] = (d2l.DATA_URL + 'pokemon.zip',
              'c065c0e2593b8b161a2d7873e42418bf6a21106c')

data_dir = d2l.download_extract('pokemon')
pokemon = torchvision.datasets.ImageFolder(data_dir)

							 

							Downloading ../data/pokemon.zip from http://d2l-data.s3-accelerate.amazonaws.com/pokemon.zip...

						

							#@save
d2l.DATA_HUB['pokemon'] = (d2l.DATA_URL + 'pokemon.zip',
              'c065c0e2593b8b161a2d7873e42418bf6a21106c')

data_dir = d2l.download_extract('pokemon')
pokemon = gluon.data.vision.datasets.ImageFolderDataset(data_dir)

							 

							Downloading ../data/pokemon.zip from http://d2l-data.s3-accelerate.amazonaws.com/pokemon.zip...

						

							#@save
d2l.DATA_HUB['pokemon'] = (d2l.DATA_URL + 'pokemon.zip',
              'c065c0e2593b8b161a2d7873e42418bf6a21106c')

data_dir = d2l.download_extract('pokemon')
batch_size = 256
pokemon = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir, batch_size=batch_size, image_size=(64, 64))

							 

							Downloading ../data/pokemon.zip from http://d2l-data.s3-accelerate.amazonaws.com/pokemon.zip...
Found 40597 files belonging to 721 classes.

我們將每個圖像調(diào)整為64×64. 變換ToTensor 會將像素值投影到[0,1]，而我們的生成器將使用 tanh 函數(shù)獲取輸出 [?1,1]. 因此我們用0.5意味著和0.5標(biāo)準(zhǔn)偏差以匹配值范圍。

							batch_size = 256
transformer = torchvision.transforms.Compose([
  torchvision.transforms.Resize((64, 64)),
  torchvision.transforms.ToTensor(),
  torchvision.transforms.Normalize(0.5, 0.5)
])
pokemon.transform = transformer
data_iter = torch.utils.data.DataLoader(
  pokemon, batch_size=batch_size,
  shuffle=True, num_workers=d2l.get_dataloader_workers())

							 

							batch_size = 256
transformer = gluon.data.vision.transforms.Compose([
  gluon.data.vision.transforms.Resize(64),
  gluon.data.vision.transforms.ToTensor(),
  gluon.data.vision.transforms.Normalize(0.5, 0.5)
])
data_iter = gluon.data.DataLoader(
  pokemon.transform_first(transformer), batch_size=batch_size,
  shuffle=True, num_workers=d2l.get_dataloader_workers())

							 

							def transform_func(X):
  X = X / 255.
  X = (X - 0.5) / (0.5)
  return X

# For TF>=2.4 use `num_parallel_calls = tf.data.AUTOTUNE`
data_iter = pokemon.map(lambda x, y: (transform_func(x), y),
            num_parallel_calls=tf.data.experimental.AUTOTUNE)
data_iter = data_iter.cache().shuffle(buffer_size=1000).prefetch(
  buffer_size=tf.data.experimental.AUTOTUNE)

							 

							WARNING:tensorflow:From /home/d2l-worker/miniconda3/envs/d2l-en-release-1/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.
Instructions for updating:
Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089

						

讓我們想象一下前 20 張圖像。

							warnings.filterwarnings('ignore')
d2l.set_figsize((4, 4))
for X, y in data_iter:
  imgs = X[:20,:,:,:].permute(0, 2, 3, 1)/2+0.5
  d2l.show_images(imgs, num_rows=4, num_cols=5)
  break

							 

							d2l.set_figsize((4, 4))
for X, y in data_iter:
  imgs = X[:20,:,:,:].transpose(0, 2, 3, 1)/2+0.5
  d2l.show_images(imgs, num_rows=4, num_cols=5)
  break

							 

							d2l.set_figsize(figsize=(4, 4))
for X, y in data_iter.take(1):
  imgs = X[:20, :, :, :] / 2 + 0.5
  d2l.show_images(imgs, num_rows=4, num_cols=5)

							 