[MXNet逐梦之旅]练习四·使用MXNetFashionMNIST数据集分类简洁实现
import sys
import time
from mxnet import gluon as gl
import mxnet as mx
from matplotlib import pyplot as plt
from mxnet import autograd, nd
import numpy as np
mnist_train = gl.data.vision.FashionMNIST(root="fashion-mnist/",train=True)
mnist_test = gl.data.vision.FashionMNIST(root="fashion-mnist/",train=False)
print(len(mnist_train), len(mnist_test))
"""我也遇到这个问题，想用之前下载好的数据集直接使用。但是由于MXNet的MNIST数据集读取的机制会去验证数据集的正确性，所以我使用的用keras下载的数据集放到相关位置，MXNet还是还是会去下载。
解决方法，我用MXNet下载了好了fashion-mnist数据集，上传了，大家可以直接下载到相应位置解压即可。
也可以从采用自定义位置的方式 ：_mnist_train = gl.data.vision.FashionMNIST(root="fashion-mnist/",train=True)_
只需放到编写代码处解压即可。。"""
batch_size = 100
transformer = gl.data.vision.transforms.ToTensor()
if sys.platform.startswith('win'):
num_workers = 0
else:
num_workers = 4
train_iter = gl.data.DataLoader(mnist_train.transform_first(transformer),
batch_size, shuffle=True,
num_workers=num_workers)
test_iter = gl.data.DataLoader(mnist_test.transform_first(transformer),
1000, shuffle=False,
num_workers=num_workers)
def get_fashion_mnist_labels(labels):
text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
return([text_labels[int(i.asnumpy())] for i in labels])
def show_img(x,y):
plt.figure("Image")
plt.imshow(x.asnumpy()*255)
plt.title(get_fashion_mnist_labels(y))
plt.show()
"""start = time.time()
for X, y in train_iter:
break
print('%.2f sec' % (time.time() - start))"""
model = gl.nn.Sequential()
model.add(gl.nn.Dense(256,activation="relu"))
model.add()
model.add(gl.nn.Dense(10))
model.initialize(mx.init.Normal(sigma=0.01))
lr = 0.1
loss = gl.loss.SoftmaxCrossEntropyLoss()
trainer = gl.Trainer(model.collect_params(), 'sgd', {'learning_rate': lr})
def accuracy(y_hat, y):
return (y_hat.argmax(axis=1) == y.astype('float32')).mean().asscalar()
num_epochs = 10
for epoch in range(1, num_epochs + 1):
losses = []
for X, y in train_iter:
with autograd.record():
l = loss(model(X), y)
losses.append(l.asnumpy())
l.backward()
trainer.step(batch_size)
loss_sum = np.mean(losses)
for Xt, yt in test_iter:
accy = accuracy(model(Xt),yt)
break
print('epoch %d, loss: %f, accy: %f' % (epoch,loss_sum,accy))
60000 10000
epoch 1, loss: 0.773934, accy: 0.812000
epoch 2, loss: 0.490065, accy: 0.855000
epoch 3, loss: 0.436965, accy: 0.852000
epoch 4, loss: 0.401657, accy: 0.875000
epoch 5, loss: 0.380360, accy: 0.856000
epoch 6, loss: 0.363831, accy: 0.869000
epoch 7, loss: 0.349141, accy: 0.873000
epoch 8, loss: 0.337938, accy: 0.877000
epoch 9, loss: 0.326593, accy: 0.874000
epoch 10, loss: 0.319641, accy: 0.884000
