无限循环中的凯拉斯的发电机

Question

all，

我对Francois Chollet的《深度学习与Python》一书中的代码有问题：

import numpy as np
import os
import sys
from matplotlib import pyplot as plt
def generator(data, lookback, delay, min_index, max_index,
shuffle=False, batch_size=128, step=6):
   if max_index is None:
      max_index = len(data) - delay - 1
   i = min_index + lookback
#   for it in range(1):
   while True:
      if shuffle:
         rows = np.random.randint(
              min_index + lookback, max_index, size=batch_size)
      else:
         if i + batch_size >= max_index:
              i = min_index + lookback
         rows = np.arange(i, min(i + batch_size, max_index))
         i += len(rows)
      samples = np.zeros((len(rows),
                   lookback // step,
                   data.shape[-1]))
      targets = np.zeros((len(rows),))
      for j, row in enumerate(rows):
        indices = range(rows[j] - lookback, rows[j], step)
        samples[j] = data[indices]
        targets[j] = data[rows[j] + delay][1]
   yield samples, targets
data_dir = os.path.join(os.getcwd(),'jena_climate')
fname = os.path.join(data_dir, 'jena_climate_2009_2016.csv')
f = open(fname)
data = f.read()
f.close()
lines = data.split('n')
header = lines[0].split(',')
lines = lines[1:]
print(header)
print(len(lines))
float_data = np.zeros((len(lines), len(header) - 1))
for i, line in enumerate(lines):
       values = [float(x) for x in line.split(',')[1:]]
       float_data[i, :] = values
# temp = float_data[:, 1] 
# plt.plot(range(len(temp)), temp)
# plt.show()
mean = float_data[:200000].mean(axis=0)
float_data -= mean
std = float_data[:200000].std(axis=0)
float_data /= std
lookback = 1440
step = 6
delay = 144
batch_size = 128
train_gen = generator(float_data,
lookback=lookback,
delay=delay,
min_index=0,
max_index=200000,
shuffle=True,
step=step,
batch_size=batch_size)
val_gen = generator(float_data,
lookback=lookback,
delay=delay,
min_index=200001,
max_index=300000,
step=step,
batch_size=batch_size)
test_gen = generator(float_data,
lookback=lookback,
delay=delay,
min_index=300001,
max_index=None,
step=step,
batch_size=batch_size)
# samples,targets=next(train_gen)
val_steps = (300000 - 200001 - lookback)
test_steps = (len(float_data) - 300001 - lookback)
# print(val_steps)
def evaluate_naive_method():
    batch_maes = []
    for step in range(val_steps):
        samples, targets = next(val_gen) 
        print(step)
        preds = samples[:, -1, 1]
        mae = np.mean(np.abs(preds - targets))
        batch_maes.append(mae)
    print(np.mean(batch_maes))
evaluate_naive_method()

代码定义了生成器函数，以生成温度预测示例的样品。但是，在Ubuntu Linux下的Python 3.6.8安装后，发电机仍处于无限循环中，并且生成验证数据从未执行的环路。我在这里看到了类似的问题。显然，在Python 3中正确处理发电机是一个小问题。有人知道如何规避这个吗？

Answer 1

是的，这是因为收益率语句的凹痕被弄乱了。应将其封闭在while True循环中，以在环路的每次迭代中产生批处理。更改：

while True:
    ### other code
yield samples, targets

to

while True:
    ### other code
    yield samples, targets