Question

我对机器学习非常陌生，我正在尝试在keras中实现我的自定义层。我找到了一些教程，似乎比较简单。不过，我不了解的是如何在Sequential（）中实现我的新自定义层。例如，请参阅我从tensorflow网站（https://www.tensorflow.org/tutorials/keras/basic_text_classification）处理的此分类问题，为方便起见，发布在此处：

from __future__ import absolute_import, division, print_function

import tensorflow as tf
from tensorflow import keras
import numpy as np


imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()
# The first indices are reserved
word_index = {k:(v+3) for k,v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown
word_index["<UNUSED>"] = 3

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

train_data = keras.preprocessing.sequence.pad_sequences(train_data,
                                                        value=word_index["<PAD>"],
                                                        padding='post',
                                                        maxlen=256)

test_data = keras.preprocessing.sequence.pad_sequences(test_data,
                                                       value=word_index["<PAD>"],
                                                       padding='post',
                                                       maxlen=256)

# input shape is the vocabulary count used for the movie reviews (10,000 words)
vocab_size = 10000

model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))

model.summary()

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['acc'])

x_val = train_data[:10000]
partial_x_train = train_data[10000:]

y_val = train_labels[:10000]
partial_y_train = train_labels[10000:]

history = model.fit(partial_x_train,
                    partial_y_train,
                    epochs=40,
                    batch_size=512,
                    validation_data=(x_val, y_val),
                    verbose=1)

results = model.evaluate(test_data, test_labels)

print(results)

我是否必须更改keras.Sequential（）的源代码，还是有一种简单的方法？

此外，查看类Sequential（）的源代码使我感到困惑：我无法弄清楚'summary（）'，'compile（）'，'fit（）'和'evaluate（） ”）（如果此类的源代码中甚至没有提供）都可以调用。这是Sequential（）的源代码：

https://github.com/keras-team/keras/blob/a1397169ddf8595736c01fcea084c8e34e1a3884/keras/engine/sequential.py

Answer 1

Sequential是一个模型，而不是一个层。

您提到的功能（summary，compile，fit，evaluate）在Model class linked here中实现，因为Sequential是Model的子类。

如果要编写自定义图层，则应该改为继承Layer，而不是Model或Sequential。

您需要实现build，call和compute_output_shape来创建自己的图层。

有一些examples on the Keras documentation：

from keras import backend as K
from keras.layers import Layer

class MyLayer(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        super(MyLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.kernel = self.add_weight(name='kernel', 
                                  shape=(input_shape[1], self.output_dim),
                                  initializer='uniform',
                                  trainable=True)
        super(MyLayer, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        return K.dot(x, self.kernel)

    def compute_output_shape(self, input_shape):
        return (input_shape[0], self.output_dim)

要使用它，请从您放入的文件中导入MyLayer类，然后像默认的Keras图层一样添加它：

from custom.layers import MyLayer

model = keras.Sequential()
model.add(MyLayer())

如果源代码中没有这些函数，该如何调用Sequential（）类的函数？

1 个答案: