.. _sec_mlp-implementation:
多層パーセプトロンの実装
========================
多層パーセプトロン（MLP）は、単純な線形モデルよりも実装がそれほど複雑になるわけではありない。重要な概念上の違いは、複数の層を連結するようになったことである。
.. 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
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
from jax import numpy as jnp
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import tensorflow as d2l
import tensorflow as tf
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLPScratch(d2l.Classifier):
def __init__(self, num_inputs, num_outputs, num_hiddens, lr, sigma=0.01):
super().__init__()
self.save_hyperparameters()
self.W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens) * sigma)
self.b1 = nn.Parameter(torch.zeros(num_hiddens))
self.W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs) * sigma)
self.b2 = nn.Parameter(torch.zeros(num_outputs))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLPScratch(d2l.Classifier):
def __init__(self, num_inputs, num_outputs, num_hiddens, lr, sigma=0.01):
super().__init__()
self.save_hyperparameters()
self.W1 = np.random.randn(num_inputs, num_hiddens) * sigma
self.b1 = np.zeros(num_hiddens)
self.W2 = np.random.randn(num_hiddens, num_outputs) * sigma
self.b2 = np.zeros(num_outputs)
for param in self.get_scratch_params():
param.attach_grad()
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLPScratch(d2l.Classifier):
num_inputs: int
num_outputs: int
num_hiddens: int
lr: float
sigma: float = 0.01
def setup(self):
self.W1 = self.param('W1', nn.initializers.normal(self.sigma),
(self.num_inputs, self.num_hiddens))
self.b1 = self.param('b1', nn.initializers.zeros, self.num_hiddens)
self.W2 = self.param('W2', nn.initializers.normal(self.sigma),
(self.num_hiddens, self.num_outputs))
self.b2 = self.param('b2', nn.initializers.zeros, self.num_outputs)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLPScratch(d2l.Classifier):
def __init__(self, num_inputs, num_outputs, num_hiddens, lr, sigma=0.01):
super().__init__()
self.save_hyperparameters()
self.W1 = tf.Variable(
tf.random.normal((num_inputs, num_hiddens)) * sigma)
self.b1 = tf.Variable(tf.zeros(num_hiddens))
self.W2 = tf.Variable(
tf.random.normal((num_hiddens, num_outputs)) * sigma)
self.b2 = tf.Variable(tf.zeros(num_outputs))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def relu(X):
return np.maximum(X, 0)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def relu(X):
return jnp.maximum(X, 0)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def relu(X):
return tf.math.maximum(X, 0)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLP(d2l.Classifier):
def __init__(self, num_outputs, num_hiddens, lr):
super().__init__()
self.save_hyperparameters()
self.net = nn.Sequential(nn.Flatten(), nn.LazyLinear(num_hiddens),
nn.ReLU(), nn.LazyLinear(num_outputs))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLP(d2l.Classifier):
def __init__(self, num_outputs, num_hiddens, lr):
super().__init__()
self.save_hyperparameters()
self.net = nn.Sequential()
self.net.add(nn.Dense(num_hiddens, activation='relu'),
nn.Dense(num_outputs))
self.net.initialize()
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLP(d2l.Classifier):
num_outputs: int
num_hiddens: int
lr: float
@nn.compact
def __call__(self, X):
X = X.reshape((X.shape[0], -1)) # Flatten
X = nn.Dense(self.num_hiddens)(X)
X = nn.relu(X)
X = nn.Dense(self.num_outputs)(X)
return X
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class MLP(d2l.Classifier):
def __init__(self, num_outputs, num_hiddens, lr):
super().__init__()
self.save_hyperparameters()
self.net = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(num_hiddens, activation='relu'),
tf.keras.layers.Dense(num_outputs)])
.. raw:: html
.. raw:: html