python生成器generator:深度学习读取batch图片的操作

>>> L = [x * x for x in range(10)]
>>> L
[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]
>>> g = (x * x for x in range(10))
>>> g
<generator object <genexpr> at 0x1022ef630>

>>> g = (x * x for x in range(10))
>>> for n in g:
...     print(n)

def fib(max):
    n, a, b = 0, 0, 1
    while n < max:
        print(b)
        a, b = b, a + b
        n = n + 1
    return 'done'

def fib(max):
    n, a, b = 0, 0, 1
    while n < max:
        yield b
        a, b = b, a + b
        n = n + 1
    return 'done'

>>> f = fib(6)
>>> f
<generator object fib at 0x104feaaa0>

>>> for n in fib(6):
...     print(n)
...

def train_data(train_file,batch_size,resize_shape):
    datas, labels = read_data(train_file)
    num_batch = len(datas)//batch_size
    for i in range(num_batch):
        imgs = []
        train_datas = datas[batch_size*i:batch_size*(i+1)]
        train_lables = labels[batch_size*i:batch_size*(i+1)]
        for img_path in train_datas:
            img = cv2.imread(img_path)
            img = cv2.resize(img,resize_shape)
            img = img/255 #归一化处理
            imgs.append(img)
        yield np.array(imgs),np.array(train_lables)

from keras.datasets import imdb
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras import layers
import numpy as np
import random
from sklearn.metrics import f1_score, accuracy_score

max_features = 100
maxlen = 50
batch_size = 320
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
x_train = pad_sequences(x_train, maxlen=maxlen)
x_test = pad_sequences(x_test, maxlen=maxlen)

def generator():
    while 1:
        row = np.random.randint(0, len(x_train), size=batch_size)
        x = np.zeros((batch_size, x_train.shape[-1]))
        y = np.zeros((batch_size,))
        x = x_train[row]
        y = y_train[row]
        yield x, y

# generator()
model = Sequential()
model.add(layers.Embedding(max_features, 32, input_length=maxlen))
model.add(layers.GRU(64, return_sequences=True))
model.add(layers.GRU(32))
# model.add(layers.Flatten())
# model.add(layers.Dense(32,activation='relu'))

model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
print(model.summary())

# history = model.fit(x_train, y_train, epochs=1,batch_size=32, validation_split=0.2)
# Keras中的fit()函数传入的x_train和y_train是被完整的加载进内存的,当然用起来很方便，但是如果我们数据量很大，
# 那么是不可能将所有数据载入内存的，必将导致内存泄漏，这时候我们可以用fit_generator函数来进行训练。
# fit_generator函数必须传入一个生成器，我们的训练数据也是通过生成器产生的
history = model.fit_generator(generator(), epochs=1, steps_per_epoch=len(x_train) // (batch_size))

print(model.evaluate(x_test, y_test))
y = model.predict_classes(x_test)
print(accuracy_score(y_test, y))