機器學習筆記(6)：多類邏輯迴歸-使用gluon

上一篇演示了純手動新增隱藏層，這次使用gluon讓程式碼更精減，程式碼來自：https://zh.gluon.ai/chapter_supervised-learning/mlp-gluon.html

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(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)
  
#計算模型
net = gluon.nn.Sequential()
with net.name_scope():
    net.add(gluon.nn.Flatten())
    net.add(gluon.nn.Dense(256, activation="relu"))
    net.add(gluon.nn.Dense(10))
net.initialize()
  
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()

#定義訓練器
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})
 
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)
  
for epoch in range(5):
    train_loss = 0.
    train_acc = 0.
    for data, label in train_data:
        with autograd.record():
            output = net(data)
            loss = softmax_cross_entropy(output, label)
        loss.backward()
        trainer.step(batch_size) #使用訓練器，向"前"走一步

        train_loss += nd.mean(loss).asscalar()
        train_acc += accuracy(output, label)

    test_acc = evaluate_accuracy(test_data, net)
    print("Epoch %d. Loss: %f, Train acc %f, Test acc %f" % (
        epoch, train_loss/len(train_data), train_acc/len(train_data), test_acc))

data, label = mnist_test[0:10]
show_images(data)
print('true labels')
print(get_text_labels(label))
  
predicted_labels = net(data).argmax(axis=1)
print('predicted labels')
print(get_text_labels(predicted_labels.asnumpy()))

有變化的地方，已經加上了註釋。執行效果，跟一篇完全相同，就不重複貼圖了

機器學習筆記(6)：多類邏輯迴歸-使用gluon

相關文章