import matplotlib.pyplot as pltimport mxnet as mx
from mxnet import gluon
from mxnet import ndarray as nd
from mxnet import autograd
def transform(data, label):
return data.astype('float32')/255, label.astype('float32')
mnist_train = gluon.data.vision.fashionmnist(train=true, transform=transform)
mnist_test = gluon.data.vision.fashionmnist(train=false, transform=transform)
def show_images(images):
n = images.shape[0]
_, figs = plt.subplots(1, n, figsize=(15, 15))
for i in range(n):
figs[i].imshow(images[i].reshape((28, 28)).asnumpy())
figs[i].axes.get_xaxis().set_visible(false)
figs[i].axes.get_yaxis().set_visible(false)
plt.show()
def get_text_labels(label):
text_labels = [
't 恤', '長 褲', '套頭衫', '裙 子', '外 套',
'涼 鞋', '襯 衣', '運動鞋', '包 包', '短 靴'
]return [text_labels[int(i)] for i in label]
data, label = mnist_train[0:10]
print('example shape: ', data.shape, 'label:', label)
show_images(data)
print(get_text_labels(label))
batch_size = 256
train_data = gluon.data.dataloader(mnist_train, batch_size, shuffle=true)
test_data = gluon.data.dataloader(mnist_test, batch_size, shuffle=false)
num_inputs = 784
num_outputs = 10
w = nd.random_normal(shape=(num_inputs, num_outputs))
b = nd.random_normal(shape=num_outputs)
params = [w, b]
for param in params:
param.attach_grad()
def accuracy(output, label):
return nd.mean(output.argmax(axis=1) == label).asscalar()
def _get_batch(batch):
if isinstance(batch, mx.io.databatch):
data = batch.data[0]
label = batch.label[0]
else:
data, label = batch
return data, label
def evaluate_accuracy(data_iterator, net):
acc = 0.
if isinstance(data_iterator, mx.io.mxdataiter):
data_iterator.reset()
for i, batch in enumerate(data_iterator):
data, label = _get_batch(batch)
output = net(data)
acc += accuracy(output, label)
return acc / (i+1)
#使用gluon定義計算模型
net = gluon.nn.sequential()
with net.name_scope():
net.add(gluon.nn.flatten())
net.add(gluon.nn.dense(10))
net.initialize()
#損失函式(使用交叉熵函式)
softmax_cross_entropy = gluon.loss.softmaxcrossentropyloss()
#使用梯度下降法生成訓練器，並設定學習率為0.1
trainer = gluon.trainer(net.collect_params(), 'sgd', )
for epoch in range(5):
train_loss = 0.
train_acc = 0.
for data, label in train_data:
with autograd.record():
output = net(data)
#計算損失
loss = softmax_cross_entropy(output, label)
loss.backward()
#使用sgd的trainer繼續向前"走一步"
相對之前的版本可以發現，幾乎相同的引數，但是準確度有所提公升，從0.7幾上公升到0.8幾，10個里錯誤的**數從4個下降到3個，說明gluon在一些細節上做了更好的優化。關於優化的細節，這裡有一些討論，供參考
機器學習筆記 6 多類邏輯回歸 使用gluon
from mxnet import gluon from mxnet import ndarray as nd import matplotlib.pyplot as plt import mxnet as mx from mxnet import autograd def transform da...
機器學習4 邏輯回歸與線性回歸
1 model 2 loss function 線性回歸損失函式由均方差來衡量 邏輯回歸由交叉熵衡量。邏輯回歸的loss function由training data來決定，模型需確保training data分類正確率最大，假設training data為 求上述概率公式最大化即可得到模型引數。這...
機器學習筆記 7 邏輯回歸
邏輯回歸 logistic 實際上是線性回歸推導出來的。而且是一種分類學習方法。由於簡單的二分類0 1影象不連續，我們想找到一種連續且可微的函式替換他。logistic function 正是這樣乙個函式 y 11 e z看看圖 是通過邏輯回歸根據花萼和花瓣的大小區別出是 0花 還是 1花 codi...