from __future__ import print_function
import mxnet as mx
from mxnet import nd, autograd
from mxnet import gluon
import numpy as np
mx.random.seed(1)
ctx = mx.cpu()

batch_size = 64

def transform(data, label):
    return nd.transpose(data.astype(np.float32), (2,0,1))/255, label.astype(np.float32)

train_data 
 
= mx.gluon.data.DataLoader(mx.gluon.data.vision.MNIST(train=True, transform=transform),
                                      batch_size, shuffle=True)
test_data = mx.gluon.data.DataLoader(mx.gluon.data.vision.MNIST(train=False, transform=transform),
                                     batch_size, shuffle
 
=False)

from mxnet.gluon import nn

def vgg_block(num_convs, channels):
    out = nn.Sequential()
    for _ in range(num_convs):
        out.add(nn.Conv2D(channels=channels, kernel_size=3,
                      padding=1, activation=‘relu‘))
    out.add(nn.MaxPool2D(pool_size=2, strides=2))
    return
 
 out

def vgg_stack(architecture):
    out = nn.Sequential()
    for (num_convs, channels) in architecture:
        out.add(vgg_block(num_convs, channels))
    return out

num_outputs = 10
architecture = ((1,64), (1,128), (2,256), (2,512))
net = nn.Sequential()
with net.name_scope():
    net.add(vgg_stack(architecture))
    net.add(nn.Flatten())
    net.add(nn.Dense(512, activation="relu"))
    net.add(nn.Dropout(.5))
    net.add(nn.Dense(512, activation="relu"))
    net.add(nn.Dropout(.5))
    net.add(nn.Dense(num_outputs))

net.collect_params().initialize(mx.init.Xavier(magnitude=2.24), ctx=ctx)
trainer = gluon.Trainer(net.collect_params(), ‘sgd‘, {‘learning_rate‘: .05})
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()

def accuracy(output, label):
    return nd.mean(output.argmax(axis=1)==label).asscalar()

def evaluate_accuracy(data_iterator, net):
    acc = mx.metric.Accuracy()
    for d, l in data_iterator:
        data = d.as_in_context(ctx)
        label = l.as_in_context(ctx)
        output = net(data)
        predictions = nd.argmax(output, axis=1)
        acc.update(preds=predictions, labels=label)
    return acc.get()[1]

epochs = 5
smoothing_constant = .01

for epoch in range(5):
    train_loss = 0.
    train_acc = 0.
    for data, label in train_data:
        label = label.as_in_context(ctx)
        with autograd.record():
            output = net(data)
            loss = softmax_cross_entropy(output, label)
        loss.backward()
        trainer.step(batch_size)
        
        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))

gluon實現VGG