mxnet-訓練器與分批讀取樣本
阿新 • • 發佈：2018-11-15
sets rate boot shuffle dataset cpu utf text mali
? (3): MaxPool2D(size=(2, 2), stride=(2, 2), padding=(0, 0), ceil_mode=False)
? (4): Flatten
? (5): Dense(None -> 120, Activation(relu))
? (6): Dense(None -> 84, Activation(relu))
? (7): Dense(None -> 10, linear)
)
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Fri Aug 10 16:13:29 2018
@author: myhaspl
"""
from mxnet import nd, gluon, init, autograd
from mxnet.gluon import nn
from mxnet.gluon.data.vision import datasets,transforms
import matplotlib.pyplot as plt
from time import time
mnist_train = datasets.FashionMNIST(train=True)
X, y = mnist_train[0]
print (‘X shape: ‘, X.shape, ‘X dtype‘, X.dtype, ‘y:‘, y,‘Y dtype‘, y.dtype)
#x:(height, width, channel)
#y:numpy.scalar，標簽
text_labels = [
‘t-shirt‘, ‘trouser‘, ‘pullover‘, ‘dress‘, ‘coat‘,
‘sandal‘, ‘shirt‘, ‘sneaker‘, ‘bag‘, ‘ankle boot‘
]
X, y = mnist_train[0:6]#取6個樣本
_, figs = plt.subplots(1, X.shape[0], figsize=(15, 15))
for f,x,yi in zip(figs, X,y):
# 3D->2D by removing the last channel dim
f.imshow(x.reshape((28,28)).asnumpy())
ax = f.axes
ax.set_title(text_labels[int(yi)])
ax.title.set_fontsize(20)
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
#轉換圖像為(channel, height, weight)格式，並且為floating數據類型，通過transforms.ToTensor。
#另外，normalize所有像素值 使用 transforms.Normalize平均值0.13和標準差0.31.
transformer = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(0.13, 0.31)])
#只轉換第一個元素，圖像部分。第二個元素為標簽。
mnist_train = mnist_train.transform_first(transformer)
#加載批次數據
batch_size = 200
train_data = gluon.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=4)
#讀取本批數據
i=1
for data, label in train_data:
print i
print data,label
break#沒有這一行，會以每批次200個數據來讀取。
mnist_valid = gluon.data.vision.FashionMNIST(train=False)
valid_data = gluon.data.DataLoader(mnist_valid.transform_first(transformer),batch_size=batch_size, num_workers=4)
#定義網絡
net = nn.Sequential()
net.add(nn.Conv2D(channels=6,kernel_size=5,activation="relu"),
nn.MaxPool2D(pool_size=2, strides=2),
nn.Conv2D(channels=16, kernel_size=3, activation="relu"),
nn.MaxPool2D(pool_size=2, strides=2),
nn.Flatten(),
nn.Dense(120, activation="relu"),
nn.Dense(84, activation="relu"),
nn.Dense(10))
net.initialize(init=init.Xavier())
print net
#輸出softmax與誤差
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()
#定義訓練器
trainer = gluon.Trainer(net.collect_params(), ‘sgd‘, {‘learning_rate‘: 0.1})-0.41935483
? ? -0.41935483]
? ?[-0.41935483 -0.41935483 -0.41935483 ... -0.41935483 -0.41935483
? ? -0.41935483]]]]
<NDArray 200x1x28x28 @cpu_shared(0)>?
[9 0 9 ... 3 8 5]
<NDArray 200 @cpu_shared(0)>
Sequential(
? (0): Conv2D(None -> 6, kernel_size=(5, 5), stride=(1, 1))
? (1): MaxPool2D(size=(2, 2), stride=(2, 2), padding=(0, 0), ceil_mode=False)
? (3): MaxPool2D(size=(2, 2), stride=(2, 2), padding=(0, 0), ceil_mode=False)
? (4): Flatten
? (5): Dense(None -> 120, Activation(relu))
? (6): Dense(None -> 84, Activation(relu))
? (7): Dense(None -> 10, linear)
)
mxnet-訓練器與分批讀取樣本