def test(self, test_iter, W, b):
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(
self.net(X, W, b).argmax(dim=1).numpy())
titles = [
true + '\n' + pred for true, pred in zip(true_labels, pred_labels)
]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
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 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])
def method0():
#batch_size = 256
#train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
#num_inputs = 28 * 28
#num_outputs = 10
#w = nd.random.normal(scale=0.01, shape=(num_inputs, num_outputs))
#b = nd.zeros(num_outputs)
#w.attach_grad()
#b.attach_grad()
c = evaluate_accuracy(train_iter, net, w, b, num_inputs)
# print(c)
num_epochs, lr = 5, 0.1
train_ch3(net, w, b, num_inputs, train_iter, test_iter, cross_entropy,
num_epochs, batch_size, [w, b], 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, w, b, num_inputs).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 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[ ]:
[W, b], lr)
# %% [markdown]
# ## 预测
#
# 训练完成后，现在就可以演示如何对图像进行分类了。给定一系列图像（第三行图像输出），我们比较一下它们的真实标签（第一行文本输出）和模型预测结果（第二行文本输出）。
# %%
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[10:19], titles[10:19])
# %% [markdown]
# ## 小结
#
# * 可以使用softmax回归做多类别分类。与训练线性回归相比，你会发现训练softmax回归的步骤和它非常相似：获取并读取数据、定义模型和损失函数并使用优化算法训练模型。事实上，绝大多数深度学习模型的训练都有着类似的步骤。
#
# ## 练习
#
# * 在本节中，我们直接按照softmax运算的数学定义来实现softmax函数。这可能会造成什么问题？（提示：试一试计算$\exp(50)$的大小。）
# * 本节中的`cross_entropy`函数是按照[“softmax回归”](softmax-regression.ipynb)一节中的交叉熵损失函数的数学定义实现的。这样的实现方式可能有什么问题？（提示：思考一下对数函数的定义域。）
# * 你能想到哪些办法来解决上面的两个问题？
#
#
#
# ## 扫码直达[讨论区](https://discuss.gluon.ai/t/topic/741)
def showPlt(self):
X, y = self.info()
d2l.show_fashion_mnist(X, d2l.get_fashion_mnist_labels(y))
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])
else:
trainer.step(batch_size)
y = y.astype('float32')
train_l_sum += l.asscalar()
train_acc_sum += (y_hat.argmax(axis=1) == y).sum().asscalar()
n += y.size
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size,
[W, b], lr)
# show some results
'''
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])
'''
# 1. loss function 这么定义可能存在什么问题？
# 2. softmax 运算这么定义可能存在什么问题？数值不稳定问题
