.. _sec_vgg:
ブロックを用いたネットワーク（VGG）
===================================
AlexNet は、深い CNN
が良い結果を達成できるという実証的証拠を示したが、その後の研究者が新しいネットワークを設計する際の一般的なひな形は提示しませんでした。以下の節では、深層ネットワークの設計によく用いられるいくつかのヒューリスティックな概念を紹介する。
この分野の進歩は、チップ設計における VLSI（very large scale
integration）の進歩を思わせる。そこでは、エンジニアはトランジスタの配置から論理要素へ、さらに論理ブロックへと移っていった
:cite:`Mead.1980`\ 。同様に、ニューラルネットワークアーキテクチャの設計も徐々に抽象化が進み、研究者は個々のニューロンから層全体へ、そして現在では層の反復パターンであるブロックへと考えるようになった。さらに10年後の現在では、研究者が学習済みのモデル全体を別の、とはいえ関連するタスクに転用するところまで進んでいる。このような大規模な事前学習済みモデルは、通常
*foundation models* と呼ばれる :cite:`bommasani2021opportunities`\ 。
話をネットワーク設計に戻そう。ブロックを用いるという考え方は、オックスフォード大学の
Visual Geometry Group（VGG）による、同名の *VGG*
ネットワークで最初に現れた
:cite:`Simonyan.Zisserman.2014`\ 。ループとサブルーチンを使えば、現代のどの深層学習フレームワークでも、こうした反復構造をコードで簡単に実装できる。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import torch as d2l
import torch
from torch import nn
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import mxnet as d2l
from mxnet import np, npx, init
from mxnet.gluon import nn
npx.set_np()
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import jax as d2l
from flax import linen as nn
import jax
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
import tensorflow as tf
from d2l import tensorflow as d2l
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def vgg_block(num_convs, out_channels):
layers = []
for _ in range(num_convs):
layers.append(nn.LazyConv2d(out_channels, kernel_size=3, padding=1))
layers.append(nn.ReLU())
layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
return nn.Sequential(*layers)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def vgg_block(num_convs, num_channels):
blk = nn.Sequential()
for _ in range(num_convs):
blk.add(nn.Conv2D(num_channels, kernel_size=3,
padding=1, activation='relu'))
blk.add(nn.MaxPool2D(pool_size=2, strides=2))
return blk
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def vgg_block(num_convs, out_channels):
layers = []
for _ in range(num_convs):
layers.append(nn.Conv(out_channels, kernel_size=(3, 3), padding=(1, 1)))
layers.append(nn.relu)
layers.append(lambda x: nn.max_pool(x, window_shape=(2, 2), strides=(2, 2)))
return nn.Sequential(layers)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def vgg_block(num_convs, num_channels):
blk = tf.keras.models.Sequential()
for _ in range(num_convs):
blk.add(
tf.keras.layers.Conv2D(num_channels, kernel_size=3,
padding='same', activation='relu'))
blk.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))
return blk
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class VGG(d2l.Classifier):
def __init__(self, arch, lr=0.1, num_classes=10):
super().__init__()
self.save_hyperparameters()
if tab.selected('mxnet'):
self.net = nn.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(num_classes))
self.net.initialize(init.Xavier())
if tab.selected('pytorch'):
conv_blks = []
for (num_convs, out_channels) in arch:
conv_blks.append(vgg_block(num_convs, out_channels))
self.net = nn.Sequential(
*conv_blks, nn.Flatten(),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(num_classes))
self.net.apply(d2l.init_cnn)
if tab.selected('tensorflow'):
self.net = tf.keras.models.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(
tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(num_classes)]))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class VGG(d2l.Classifier):
def __init__(self, arch, lr=0.1, num_classes=10):
super().__init__()
self.save_hyperparameters()
if tab.selected('mxnet'):
self.net = nn.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(num_classes))
self.net.initialize(init.Xavier())
if tab.selected('pytorch'):
conv_blks = []
for (num_convs, out_channels) in arch:
conv_blks.append(vgg_block(num_convs, out_channels))
self.net = nn.Sequential(
*conv_blks, nn.Flatten(),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(num_classes))
self.net.apply(d2l.init_cnn)
if tab.selected('tensorflow'):
self.net = tf.keras.models.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(
tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(num_classes)]))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class VGG(d2l.Classifier):
arch: list
lr: float = 0.1
num_classes: int = 10
training: bool = True
def setup(self):
conv_blks = []
for (num_convs, out_channels) in self.arch:
conv_blks.append(vgg_block(num_convs, out_channels))
self.net = nn.Sequential([
*conv_blks,
lambda x: x.reshape((x.shape[0], -1)), # flatten
nn.Dense(4096), nn.relu,
nn.Dropout(0.5, deterministic=not self.training),
nn.Dense(4096), nn.relu,
nn.Dropout(0.5, deterministic=not self.training),
nn.Dense(self.num_classes)])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class VGG(d2l.Classifier):
def __init__(self, arch, lr=0.1, num_classes=10):
super().__init__()
self.save_hyperparameters()
if tab.selected('mxnet'):
self.net = nn.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(num_classes))
self.net.initialize(init.Xavier())
if tab.selected('pytorch'):
conv_blks = []
for (num_convs, out_channels) in arch:
conv_blks.append(vgg_block(num_convs, out_channels))
self.net = nn.Sequential(
*conv_blks, nn.Flatten(),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(0.5),
nn.LazyLinear(num_classes))
self.net.apply(d2l.init_cnn)
if tab.selected('tensorflow'):
self.net = tf.keras.models.Sequential()
for (num_convs, num_channels) in arch:
self.net.add(vgg_block(num_convs, num_channels))
self.net.add(
tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(4096, activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(num_classes)]))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
VGG(arch=((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))).layer_summary(
(1, 1, 224, 224))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Sequential output shape: torch.Size([1, 64, 112, 112])
Sequential output shape: torch.Size([1, 128, 56, 56])
Sequential output shape: torch.Size([1, 256, 28, 28])
Sequential output shape: torch.Size([1, 512, 14, 14])
Sequential output shape: torch.Size([1, 512, 7, 7])
Flatten output shape: torch.Size([1, 25088])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 10])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
VGG(arch=((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))).layer_summary(
(1, 1, 224, 224))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Sequential output shape: (1, 64, 112, 112)
Sequential output shape: (1, 128, 56, 56)
Sequential output shape: (1, 256, 28, 28)
Sequential output shape: (1, 512, 14, 14)
Sequential output shape: (1, 512, 7, 7)
Dense output shape: (1, 4096)
Dropout output shape: (1, 4096)
Dense output shape: (1, 4096)
Dropout output shape: (1, 4096)
Dense output shape: (1, 10)
[07:38:07] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for CPU
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
VGG(arch=((1, 64), (1, 128), (2, 256), (2, 512), (2, 512)),
training=False).layer_summary((1, 224, 224, 1))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Sequential output shape: (1, 112, 112, 64)
Sequential output shape: (1, 56, 56, 128)
Sequential output shape: (1, 28, 28, 256)
Sequential output shape: (1, 14, 14, 512)
Sequential output shape: (1, 7, 7, 512)
function output shape: (1, 25088)
Dense output shape: (1, 4096)
custom_jvp output shape: (1, 4096)
Dropout output shape: (1, 4096)
Dense output shape: (1, 4096)
custom_jvp output shape: (1, 4096)
Dropout output shape: (1, 4096)
Dense output shape: (1, 10)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
VGG(arch=((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))).layer_summary(
(1, 224, 224, 1))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Sequential output shape: (1, 112, 112, 64)
Sequential output shape: (1, 56, 56, 128)
Sequential output shape: (1, 28, 28, 256)
Sequential output shape: (1, 14, 14, 512)
Sequential output shape: (1, 7, 7, 512)
Sequential output shape: (1, 10)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
model = VGG(arch=((1, 16), (1, 32), (2, 64), (2, 128), (2, 128)), lr=0.01)
trainer = d2l.Trainer(max_epochs=10, num_gpus=1)
data = d2l.FashionMNIST(batch_size=128, resize=(224, 224))
if tab.selected('pytorch'):
model.apply_init([next(iter(data.get_dataloader(True)))[0]], d2l.init_cnn)
trainer.fit(model, data)
.. figure:: output_vgg_c2e09e_63_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
model = VGG(arch=((1, 16), (1, 32), (2, 64), (2, 128), (2, 128)), lr=0.01)
trainer = d2l.Trainer(max_epochs=10, num_gpus=1)
data = d2l.FashionMNIST(batch_size=128, resize=(224, 224))
if tab.selected('pytorch'):
model.apply_init([next(iter(data.get_dataloader(True)))[0]], d2l.init_cnn)
trainer.fit(model, data)
.. figure:: output_vgg_c2e09e_66_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
model = VGG(arch=((1, 16), (1, 32), (2, 64), (2, 128), (2, 128)), lr=0.01)
trainer = d2l.Trainer(max_epochs=10, num_gpus=1)
data = d2l.FashionMNIST(batch_size=128, resize=(224, 224))
if tab.selected('pytorch'):
model.apply_init([next(iter(data.get_dataloader(True)))[0]], d2l.init_cnn)
trainer.fit(model, data)
.. figure:: output_vgg_c2e09e_69_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
trainer = d2l.Trainer(max_epochs=10)
data = d2l.FashionMNIST(batch_size=128, resize=(224, 224))
with d2l.try_gpu():
model = VGG(arch=((1, 16), (1, 32), (2, 64), (2, 128), (2, 128)), lr=0.01)
trainer.fit(model, data)
.. figure:: output_vgg_c2e09e_72_0.svg
.. raw:: html
.. raw:: html