.. _sec_mlp_scratch:
Implementação de Perceptrons Multicamadas do Zero
=================================================
Agora que caracterizamos perceptrons multicamadas (MLPs)
matematicamente, vamos tentar implementar um nós mesmos. Para comparar
com nossos resultados anteriores alcançado com regressão *softmax*
(:numref:`sec_softmax_scratch`), vamos continuar a trabalhar com o
conjunto de dados de classificação de imagens Fashion-MNIST
(:numref:`sec_fashion_mnist`).
.. raw:: html
.. raw:: html
.. code:: python
from mxnet import gluon, np, npx
from d2l import mxnet as d2l
npx.set_np()
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
.. raw:: html
.. raw:: html
.. code:: python
import torch
from torch import nn
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
.. raw:: html
.. raw:: html
.. code:: python
import tensorflow as tf
from d2l import tensorflow as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = np.random.normal(scale=0.01, size=(num_inputs, num_hiddens))
b1 = np.zeros(num_hiddens)
W2 = np.random.normal(scale=0.01, size=(num_hiddens, num_outputs))
b2 = np.zeros(num_outputs)
params = [W1, b1, W2, b2]
for param in params:
param.attach_grad()
.. raw:: html
.. raw:: html
.. code:: python
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(
num_inputs, num_hiddens, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(
num_hiddens, num_outputs, requires_grad=True) * 0.01)
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]
.. raw:: html
.. raw:: html
.. code:: python
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = tf.Variable(tf.random.normal(
shape=(num_inputs, num_hiddens), mean=0, stddev=0.01))
b1 = tf.Variable(tf.zeros(num_hiddens))
W2 = tf.Variable(tf.random.normal(
shape=(num_hiddens, num_outputs), mean=0, stddev=0.01))
b2 = tf.Variable(tf.random.normal([num_outputs], stddev=.01))
params = [W1, b1, W2, b2]
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
def relu(X):
return np.maximum(X, 0)
.. raw:: html
.. raw:: html
.. code:: python
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
.. raw:: html
.. raw:: html
.. code:: python
def relu(X):
return tf.math.maximum(X, 0)
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(np.dot(X, W1) + b1)
return np.dot(H, W2) + b2
.. raw:: html
.. raw:: html
.. code:: python
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(X@W1 + b1) # Here '@' stands for matrix multiplication
return (H@W2 + b2)
.. raw:: html
.. raw:: html
.. code:: python
def net(X):
X = tf.reshape(X, (-1, num_inputs))
H = relu(tf.matmul(X, W1) + b1)
return tf.matmul(H, W2) + b2
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
loss = gluon.loss.SoftmaxCrossEntropyLoss()
.. raw:: html
.. raw:: html
.. code:: python
loss = nn.CrossEntropyLoss()
.. raw:: html
.. raw:: html
.. code:: python
def loss(y_hat, y):
return tf.losses.sparse_categorical_crossentropy(
y, y_hat, from_logits=True)
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
num_epochs, lr = 10, 0.1
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs,
lambda batch_size: d2l.sgd(params, lr, batch_size))
.. figure:: output_mlp-scratch_106d07_63_0.svg
.. raw:: html
.. raw:: html
.. code:: python
num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
.. figure:: output_mlp-scratch_106d07_66_0.svg
.. raw:: html
.. raw:: html
.. code:: python
num_epochs, lr = 10, 0.1
updater = d2l.Updater([W1, W2, b1, b2], lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
.. figure:: output_mlp-scratch_106d07_69_0.svg
.. raw:: html
.. raw:: html
.. raw:: html
.. code:: python
d2l.predict_ch3(net, test_iter)
.. figure:: output_mlp-scratch_106d07_75_0.svg
.. raw:: html
.. raw:: html
.. code:: python
d2l.predict_ch3(net, test_iter)
.. figure:: output_mlp-scratch_106d07_78_0.svg
.. raw:: html
.. raw:: html
.. code:: python
d2l.predict_ch3(net, test_iter)
.. figure:: output_mlp-scratch_106d07_81_0.svg
.. raw:: html
.. raw:: html
.. raw:: html
`Discussions `__
.. raw:: html
.. raw:: html
`Discussions `__
.. raw:: html
.. raw:: html
`Discussions `__
.. raw:: html
.. raw:: html