def basic_multilayer():
"""
基本的多层感知机实现
:return:
"""
def relu(X):
return nd.maximum(X, 0)
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(nd.dot(X, W1) + b1)
return nd.dot(H, W2) + b2
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nd.random.normal(scale=0.01, shape=(num_inputs, num_hiddens))
b1 = nd.zeros(num_hiddens)
W2 = nd.random.normal(scale=0.01, shape=(num_hiddens, num_outputs))
b2 = nd.zeros(num_outputs)
params = [W1, b1, W2, b2]
for param in params:
param.attach_grad()
loss = gloss.SoftmaxCrossEntropyLoss()
num_epochs, lr = 5, 0.5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)
def generate(self):
net = nn.Sequential()
net.add(nn.Dense(256, activation='relu'), nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.5})
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
None, None, trainer)
def method1():
num_epochs, lr, batch_size = 5, 0.5, 256
loss = gloss.SoftmaxCrossEntropyLoss()
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
net = nn.Sequential()
net.add(nn.Dense(num_hiddens1, activation="relu"),
nn.Dropout(drop_prob1),
nn.Dense(num_hiddens2, activation="relu"),
nn.Dropout(drop_prob2),
nn.Dense(num_outputs))
net.initialize(init.Normal(sigma=0.01))
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None,
None, trainer)
def Method0():
params = [w1, b1, w2, b2]
for param in params:
param.attach_grad()
loss = gloss.SoftmaxCrossEntropyLoss()
num_epochs, lr = 5, 0.5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params, lr)
for x, y in test_iter:
break
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pre_labels = d2l.get_fashion_mnist_labels(net(x).argmax(axis=1).asnumpy())
titles = [
true + '\n' + pred for true, pred in zip(true_labels, pre_labels)
]
d2l.show_fashion_mnist(x[0:9], titles[0:9])
def main():
batch_size = 256
# 下载、读取数据集
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
# 定义初始化模型
net = nn.Sequential()
net.add(nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
# 定义损失函数
loss = gloss.SoftmaxCrossEntropyLoss()
# 定义优化算法
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.01})
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
None, None, trainer)
def simple_multilayer():
"""
多层感知机简洁实现
:return:
"""
net = nn.Sequential()
net.add(nn.Dense(256, activation='relu'), nn.Dense(10))
net.add(gluon.nn.Dropout(0.2))
net.initialize(init.Normal(sigma=0.01))
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, trainer)
def dropout_gluon():
drop_prob1, drop_prob2, lr, batch_size, num_epochs = 0.2, 0.5, 0.1, 64, 50
net = nn.Sequential()
net.add(
nn.Dense(256, activation="relu"),
nn.Dropout(drop_prob1), # 在第一个全连接层后添加丢弃层
nn.Dense(256, activation="relu"),
nn.Dropout(drop_prob2), # 在第二个全连接层后添加丢弃层
nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
None, None, trainer)
def method1():
vnet = nn.Sequential()
vnet.add(nn.Dense(10))
vnet.initialize(init.Normal(sigma=0.01))
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(vnet.collect_params(), 'sgd',
{'learning_rate': 0.1})
num_epochs = 5
d2l.train_ch3(vnet, train_iter, test_iter, loss, num_epochs, batch_size,
None, None, trainer)
for x, y in test_iter:
break
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pre_labels = d2l.get_fashion_mnist_labels(vnet(x).argmax(axis=1).asnumpy())
titles = [
true + '\n' + pred for true, pred in zip(true_labels, pre_labels)
]
d2l.show_fashion_mnist(x[0:9], titles[0:9])
#softmax回归的简洁实现
#%matplotlib inline
import d2lzh as d2l
from mxnet import gluon, init
from mxnet.gluon import loss as gloss, nn
#3.10.0 获取和读取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
#3.10.1 定义和初始化模型
net = nn.Sequential()
net.add(nn.Dense(256, activation='relu'), nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
#softmax和交叉熵损失函数
loss = gloss.SoftmaxCrossEntropyLoss()
#定义优化算法
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})
#训练模型
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None,
None, trainer)
import d2lzh as d2l
from mxnet import gluon, init
from mxnet.gluon import loss as gloss, nn
bathsize = 256
trainer_iter, test_iter = d2l.load_data_fashion_mnist(bathsize)
net = nn.Sequential()
net.add(nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
loss = gloss.SoftmaxCELoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.1})
num = 5
d2l.train_ch3(net, trainer_iter, test_iter, loss, num, bathsize, None, None,
trainer)
for x, y in test_iter:
break
truelabes = d2l.get_fashion_mnist_labels(y.asnumpy())
falselabes = d2l.get_fashion_mnist_labels(net(x).argmax(axis=1).asnumpy())
title = [true + '\n' + pred for true, pred in zip(truelabes, falselabes)]
d2l.show_fashion_mnist(x[0:9], title[0:9])
def train(self):
num_epochs, lr = 5, 100.0
d2l.train_ch3(self.net, self.train_iter, self.test_iter, self.loss,
num_epochs, self.batch_size, self.params, lr)
pass
W1 = nd.random.normal(scale=0.01, shape=(number_inputs, number_hiddens))
b1 = nd.zeros(number_hiddens)
W2 = nd.random.normal(scale=0.01, shape=(number_hiddens, number_outputs))
b2 = nd.zeros(number_outputs)
parameters = [W1, b1, W2, b2]
for parameter in parameters:
parameter.attach_grad()
def relu(X):
return nd.maximum(X, 0)
def net(X):
X = X.reshape((-1, number_inputs))
H = relu(nd.dot(X, W1) + b1)
return nd.dot(H, W2) + b2
loss = gloss.SoftmaxCrossEntropyLoss()
# hyper parameter
number_epochs = 5
learning_rate = 0.5
d2l.train_ch3(net, iter_trainning, iter_testing, loss, number_epochs,
batch_size, parameters, learning_rate)
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(nd.dot(X, W1) + b1)
return nd.dot(H, W2) + b2
# In[7]:
#损失函数
loss = gloss.SoftmaxCrossEntropyLoss()
# In[8]:
num_epochs, lr = 5, 0.5
#调用了3.6中的函数
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params,
lr)
# In[9]:
for X, y in test_iter:
break
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1).asnumpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
# In[ ]:
def method0():
num_epochs, lr, batch_size = 5, 0.5, 256
loss = gloss.SoftmaxCrossEntropyLoss()
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params, lr)
return (y_hat.argmax(axis=1) == y.astype('float32')).mean().asscalar()
def evaluate_accuracy(data_iter, net):
acc_sum, n = 0.0, 0
for X, y in data_iter:
y = y.astype('float32')
acc_sum += (net(X).argmax(axis=1) == y).sum().asscalar()
n += y.size
return acc_sum / n
# *accuracy函数的小测试
print('accuracy test:', accuracy(y_hat, y))
print('accuracy,d2l_test:', d2l.evaluate_accuracy(data_iter=test_iter,
net=net))
# 6 # 训练模型 =========================================================================================
num_epoch, lr = 5, 0.1
d2l.train_ch3(net, train_iter, test_iter, cross_entropy, num_epoch, batch_size,
[W, b], lr)
# 7 # 分类预测 ========================================================
for X, y in test_iter:
break
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1).asnumpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
#
# DLN is free software; you can redistribute it and/or modify it.
#
# DLN is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#
# Contributors:
# Xiao Wang - initial implementation
import d2lzh as d2l
from mxnet import gluon, init
from mxnet.gluon import loss as gloss, nn
# load data
batch_size = 256
iter_trainning, iter_testing = d2l.load_data_fashion_mnist(batch_size)
net = nn.Sequential()
net.add(nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.1})
# hyper parameter
number_epochs = 5
d2l.train_ch3(net, iter_trainning, iter_testing, loss, number_epochs,
batch_size, None, None, trainer)
def train(self):
d2l.train_ch3(self.net, self.train_iter, self.test_iter, self.loss,
self.num_epochs, self.batch_size, None, None,
self.optimizer)
return self.model
