使用Keras model.fit_generator生成器

Posted 2021-05-04

在编写用于训练Keras模型的自定义生成器时，我最初尝试使用generator语法。所以我从yield那里得到了qazxswwied。但是，当我尝试用__next__训练我的模式时，我会得到一个错误，我的生成器不是迭代器。修复是将model.fit_generator改为yield，这也需要重新调整return的逻辑以跟踪状态。与让__next__为我工作相比，这相当麻烦。

有没有办法让我的yield工作？如果我必须使用yield语句，我将需要编写几个迭代器，这些迭代器必须具有非常笨重的逻辑。

答案

我无法调试您的代码，因为您没有发布它，但我缩写了我为语义分段项目编写的自定义数据生成器，供您用作模板：

return

用法：

def generate_data(directory, batch_size):
    """Replaces Keras' native ImageDataGenerator."""
    i = 0
    file_list = os.listdir(directory)
    while True:
        image_batch = []
        for b in range(batch_size):
            if i == len(file_list):
                i = 0
                random.shuffle(file_list)
            sample = file_list[i]
            i += 1
            image = cv2.resize(cv2.imread(sample[0]), INPUT_SHAPE)
            image_batch.append((image.astype(float) - 128) / 128)

        yield np.array(image_batch)

另一答案

我最近玩过Keras的发电机，我终于设法准备了一个例子。它使用随机数据，所以尝试在它上面教NN是没有意义的，但它是一个很好的例子，使用python生成器为Keras。

生成一些数据

model.fit_generator(
    generate_data('~/my_data', batch_size),
    steps_per_epoch=len(os.listdir('~/my_data')) // batch_size)

发电机

import numpy as np
import pandas as pd
data = np.random.rand(200,2)
expected = np.random.randint(2, size=200).reshape(-1,1)

dataFrame = pd.DataFrame(data, columns = ['a','b'])
expectedFrame = pd.DataFrame(expected, columns = ['expected'])

dataFrameTrain, dataFrameTest = dataFrame[:100],dataFrame[-100:]
expectedFrameTrain, expectedFrameTest = expectedFrame[:100],expectedFrame[-100:]

硬模型

def generator(X_data, y_data, batch_size):

  samples_per_epoch = X_data.shape[0]
  number_of_batches = samples_per_epoch/batch_size
  counter=0

  while 1:

    X_batch = np.array(X_data[batch_size*counter:batch_size*(counter+1)]).astype('float32')
    y_batch = np.array(y_data[batch_size*counter:batch_size*(counter+1)]).astype('float32')
    counter += 1
    yield X_batch,y_batch

    #restart counter to yeild data in the next epoch as well
    if counter >= number_of_batches:
        counter = 0

产量

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten, Reshape
from keras.layers.convolutional import Convolution1D, Convolution2D, MaxPooling2D
from keras.utils import np_utils


 model = Sequential()
 model.add(Dense(12, activation='relu', input_dim=dataFrame.shape[1]))
 model.add(Dense(1, activation='sigmoid'))


 model.compile(loss='binary_crossentropy', optimizer='adadelta', metrics=['accuracy'])

 #Train the model using generator vs using the full batch
 batch_size = 8

 model.fit_generator(generator(dataFrameTrain,expectedFrameTrain,batch_size), epochs=3,steps_per_epoch = dataFrame.shape[0]/batch_size, validation_data=generator(dataFrameTest,expectedFrameTest,batch_size*2),validation_steps=dataFrame.shape[0]/batch_size*2)

 #without generator
 #model.fit(x = np.array(dataFrame), y = np.array(expected), batch_size = batch_size, epochs = 3)

另一答案

这是我实现它读取任何大小的文件的方式。它就像一个魅力。

Epoch 1/3
25/25 [==============================] - 3s - loss: 0.7297 - acc: 0.4750 - 
val_loss: 0.7183 - val_acc: 0.5000
Epoch 2/3
25/25 [==============================] - 0s - loss: 0.7213 - acc: 0.3750 - 
val_loss: 0.7117 - val_acc: 0.5000
Epoch 3/3
25/25 [==============================] - 0s - loss: 0.7132 - acc: 0.3750 - 
val_loss: 0.7065 - val_acc: 0.5000

主要的背面我有

import pandas as pd

hdr=[]
for i in range(num_labels+num_features):
    hdr.append("Col-"+str(i)) # data file do not have header so I need to
                              # provide one for pd.read_csv by chunks to work

def tgen(filename):
    csvfile = open(filename)
    reader = pd.read_csv(csvfile, chunksize=batch_size,names=hdr,header=None)
    while True:
    for chunk in reader:
        W=chunk.values        # labels and features
        Y =W[:,:num_labels]   # labels 
        X =W[:,num_labels:]   # features
        X= X / 255            # any required transformation
        yield X, Y
    csvfile = open(filename)
    reader = pd.read_csv(csvfile, chunksize=batchz,names=hdr,header=None)