🏷️sec_vgg
While AlexNet offered empirical evidence that deep CNNs can achieve good results, it did not provide a general template to guide subsequent researchers in designing new networks. In the following sections, we will introduce several heuristic concepts commonly used to design deep networks.
Progress in this field mirrors that in chip design where engineers went from placing transistors to logical elements to logic blocks. Similarly, the design of neural network architectures had grown progressively more abstract, with researchers moving from thinking in terms of individual neurons to whole layers, and now to blocks, repeating patterns of layers.
The idea of using blocks first emerged from the Visual Geometry Group (VGG) at Oxford University, in their eponymously-named VGG network. It is easy to implement these repeated structures in code with any modern deep learning framework by using loops and subroutines.
The basic building block of classic CNNs
is a sequence of the following:
(i) a convolutional layer
with padding to maintain the resolution,
(ii) a nonlinearity such as a ReLU,
(iii) a pooling layer such
as a max pooling layer.
One VGG block consists of a sequence of convolutional layers,
followed by a max pooling layer for spatial downsampling.
In the original VGG paper :cite:Simonyan.Zisserman.2014,
the authors
employed convolutions with vgg_block
to implement one VGG block.
The function takes two arguments
corresponding to the number of convolutional layers num_convs
and the number of output channels num_channels.
from d2l import mxnet as d2l
from mxnet import np, npx
from mxnet.gluon import nn
npx.set_np()
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
#@tab pytorch
from d2l import torch as d2l
import torch
from torch import nn
def vgg_block(num_convs, in_channels, out_channels):
layers=[]
for _ in range(num_convs):
layers.append(nn.Conv2d(in_channels, out_channels,
kernel_size=3, padding=1))
layers.append(nn.ReLU())
in_channels = out_channels
layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
return nn.Sequential(*layers)
#@tab tensorflow
from d2l import tensorflow as d2l
import tensorflow as tf
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
Like AlexNet and LeNet,
the VGG Network can be partitioned into two parts:
the first consisting mostly of convolutional and pooling layers
and the second consisting of fully-connected layers.
This is depicted in :numref:fig_vgg.
:width:400px
🏷️fig_vgg
The convolutional part of the network connects several VGG blocks from :numref:fig_vgg (also defined in the vgg_block function)
in succession.
The following variable conv_arch consists of a list of tuples (one per block),
where each contains two values: the number of convolutional layers
and the number of output channels,
which are precisely the arguments required to call
the vgg_block function.
The fully-connected part of the VGG network is identical to that covered in AlexNet.
The original VGG network had 5 convolutional blocks, among which the first two have one convolutional layer each and the latter three contain two convolutional layers each. The first block has 64 output channels and each subsequent block doubles the number of output channels, until that number reaches 512. Since this network uses 8 convolutional layers and 3 fully-connected layers, it is often called VGG-11.
#@tab all
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))
The following code implements VGG-11. This is a simple matter of executing a for-loop over conv_arch.
def vgg(conv_arch):
net = nn.Sequential()
# The convolutional part
for (num_convs, num_channels) in conv_arch:
net.add(vgg_block(num_convs, num_channels))
# The fully-connected part
net.add(nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
nn.Dense(10))
return net
net = vgg(conv_arch)
#@tab pytorch
def vgg(conv_arch):
# The convolutional part
conv_blks=[]
in_channels=1
for (num_convs, out_channels) in conv_arch:
conv_blks.append(vgg_block(num_convs, in_channels, out_channels))
in_channels = out_channels
return nn.Sequential(
*conv_blks, nn.Flatten(),
# The fully-connected part
nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 10))
net = vgg(conv_arch)
#@tab tensorflow
def vgg(conv_arch):
net = tf.keras.models.Sequential()
# The convulational part
for (num_convs, num_channels) in conv_arch:
net.add(vgg_block(num_convs, num_channels))
# The fully-connected part
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(10)]))
return net
net = vgg(conv_arch)
Next, we will construct a single-channel data example with a height and width of 224 to observe the output shape of each layer.
net.initialize()
X = np.random.uniform(size=(1, 1, 224, 224))
for blk in net:
X = blk(X)
print(blk.name, 'output shape:\t', X.shape)
#@tab pytorch
X = torch.randn(size=(1, 1, 224, 224))
for blk in net:
X = blk(X)
print(blk.__class__.__name__,'output shape:\t',X.shape)
#@tab tensorflow
X = tf.random.uniform((1, 224, 224, 1))
for blk in net.layers:
X = blk(X)
print(blk.__class__.__name__,'output shape:\t', X.shape)
As you can see, we halve height and width at each block, finally reaching a height and width of 7 before flattening the representations for processing by the fully-connected part of the network.
Since VGG-11 is more computationally-heavy than AlexNet we construct a network with a smaller number of channels. This is more than sufficient for training on Fashion-MNIST.
#@tab mxnet, pytorch
ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
net = vgg(small_conv_arch)
#@tab tensorflow
ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
# Recall that this has to be a function that will be passed to
# `d2l.train_ch6()` so that model building/compiling need to be within
# `strategy.scope()` in order to utilize the CPU/GPU devices that we have
net = lambda: vgg(small_conv_arch)
Apart from using a slightly larger learning rate,
the model training process is similar to that of AlexNet in :numref:sec_alexnet.
#@tab all
lr, num_epochs, batch_size = 0.05, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr)
- VGG-11 constructs a network using reusable convolutional blocks. Different VGG models can be defined by the differences in the number of convolutional layers and output channels in each block.
- The use of blocks leads to very compact representations of the network definition. It allows for efficient design of complex networks.
- In their VGG paper, Simonyan and Ziserman experimented with various architectures. In particular, they found that several layers of deep and narrow convolutions (i.e.,
$3 \times 3$ ) were more effective than fewer layers of wider convolutions.
- When printing out the dimensions of the layers we only saw 8 results rather than 11. Where did the remaining 3 layer information go?
- Compared with AlexNet, VGG is much slower in terms of computation, and it also needs more GPU memory. Analyze the reasons for this.
- Try changing the height and width of the images in Fashion-MNIST from 224 to 96. What influence does this have on the experiments?
- Refer to Table 1 in the VGG paper :cite:
Simonyan.Zisserman.2014to construct other common models, such as VGG-16 or VGG-19.
:begin_tab:mxnet
Discussions
:end_tab:
:begin_tab:pytorch
Discussions
:end_tab:
:begin_tab:tensorflow
Discussions
:end_tab: