Keras TypeError: Cannot convert Type TensorType(float32, 3D) (of Variable Subtensor{:int64:}.0)

Question

下面的代码 sn-p 给了我一些 tensorType 错误

TypeError：无法将类型 TensorType(float32, 3D)（变量 Subtensor{:int64:}.0）转换为类型 TensorType(float32, (False, False, True))。您可以尝试手动将 Subtensor{:int64:}.0 转换为 TensorType(float32, (False, False, True))。

这是我正在阅读的教程网站之一的基本示例。 你能帮我理解这个错误吗？我是机器学习和 keras 的新手

import itertools
import numpy as np
# put together a model to predict 
from keras.layers import Input, Embedding, merge, Flatten, SimpleRNN
from keras.models import Model


sentences = '''
sam is red
hannah not red
hannah is green
bob is green
bob not red
sam not green
sarah is red
sarah not green'''.strip().split('\n')
is_green = np.asarray([[0, 1, 1, 1, 1, 0, 0, 0]], dtype='int32').T

lemma = lambda x: x.strip().lower().split(' ')
sentences_lemmatized = [lemma(sentence) for sentence in sentences]
words = set(itertools.chain(*sentences_lemmatized))
# set(['boy', 'fed', 'ate', 'cat', 'kicked', 'hat'])

# dictionaries for converting words to integers and vice versa
word2idx = dict((v, i) for i, v in enumerate(words))
idx2word = list(words)

# convert the sentences a numpy array
to_idx = lambda x: [word2idx[word] for word in x]
sentences_idx = [to_idx(sentence) for sentence in sentences_lemmatized]
sentences_array = np.asarray(sentences_idx, dtype='int32')

# parameters for the model
sentence_maxlen = 3
n_words = len(words)
n_embed_dims = 5

input_sentence = Input(shape=(sentence_maxlen,), dtype='int32')
input_embedding = Embedding(n_words, n_embed_dims)(input_sentence)
#color_prediction = SimpleRNN(init='uniform',output_dim=1,input_dim=3)(input_embedding)
#color_prediction = SimpleRNN(output_dim=1,input_dim=5, 
 #       init='glorot_uniform', inner_init='orthogonal', activation='sigmoid', weights=None, return_sequences=False)(input_embedding);

color_prediction = SimpleRNN(1, return_sequences=False, batch_input_shape=(10, 2, 3))(input_embedding);

predict_green = Model(input=[input_sentence], output=[color_prediction])
predict_green.compile(optimizer='sgd', loss='binary_crossentropy')

# fit the model to predict what color each person is
predict_green.fit([sentences_array], [is_green], nb_epoch=5000, verbose=1)
embeddings = predict_green.layers[1].W.get_value()

# print out the embedding vector associated with each word
for i in range(n_words):
    print('{}: {}'.format(idx2word[i], embeddings[i]))

Answer 1

我是机器学习的新手，也遇到了您的问题。 我更改了如下代码并运行，但我不确定它是否正确。

import itertools
import os
import numpy as np
from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import Embedding
from keras.layers import Input, Embedding, merge, Flatten, SimpleRNN
sentences = '''
sam is red
hannah not red
hannah is green
bob is green
bob not red
sam not green
sarah is red
sarah not green'''.strip().split('\n')
is_green = np.asarray([[0, 1, 1, 1, 1, 0, 0, 0]], dtype='int32').T
lemma = lambda x: x.strip().lower().split(' ')
sentences_lemmatized = [lemma(sentence) for sentence in sentences]
words = set(itertools.chain(*sentences_lemmatized))
# set(['boy', 'fed', 'ate', 'cat', 'kicked', 'hat'])
# dictionaries for converting words to integers and vice versa
word2idx = dict((v, i) for i, v in enumerate(words))
idx2word = list(words)
# convert the sentences a numpy array
to_idx = lambda x: [word2idx[word] for word in x]
sentences_idx = [to_idx(sentence) for sentence in sentences_lemmatized]
sentences_array = np.asarray(sentences_idx, dtype='int32')
# parameters for the model
sentence_maxlen = 3
n_words = len(words)
n_embed_dims = 3
model = Sequential()
model.add(Embedding(n_words, n_embed_dims,input_length=sentence_maxlen))
model.add(SimpleRNN(3))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])
model.fit([sentences_array], [is_green], nb_epoch=5000, verbose=1)
predictions = model.predict(sentences_array)
print predictions.shape
embeddings = model.layers[0].W.get_value()
# print out the embedding vector associated with each word
for i in range(n_words):
    print('{}: {}'.format(idx2word[i], embeddings[i]))

输出：

sarah: [-0.51089537 -0.30958903 -0.17312947] sam: [-0.47487321
-0.33426151 -0.18260512] hannah: [ 0.51548952  0.33343625  0.18121554] is: [ 0.02989657 -0.02573686  0.01081978] green: [ 0.0155487 
-0.02551323  0.00846179] not: [ 0.01339869 -0.02586824  0.01932905] bob: [ 0.47654441  0.37283263  0.17969941] red: [-0.02136148 
0.04420395 -0.03119873]

Answer 2

作为参考，此示例代码来自 http://benjaminbolte.com/blog/2016/keras-language-modeling.html，尽管从 2016 年 4 月开始，它不适用于当前版本的 Keras==1.1.1、Theano==0.8.2

在发布博文时，我也使用了这段代码，修改它以使用 LSTM，现在还注意到它不再使用最新的 Keras/Theano 运行。

我认为你需要的主要东西，尤其是使用新的 Keras-1 功能 API 是在SimpleRNN 之后的最后一个Dense 层。您还需要确保您的SimpleRNN 的output_dim 为3。

我修改了最低限度以使您的代码正常工作，这是运行的更新代码并提供以下输出：

import itertools
import numpy as np
# put together a model to predict
from keras.layers import Input, Embedding, merge, Flatten, Dense, SimpleRNN
from keras.models import Model


sentences = '''
sam is red
hannah not red
hannah is green
bob is green
bob not red
sam not green
sarah is red
sarah not green'''.strip().split('\n')
is_green = np.asarray([[0, 1, 1, 1, 1, 0, 0, 0]], dtype='int32').T

lemma = lambda x: x.strip().lower().split(' ')
sentences_lemmatized = [lemma(sentence) for sentence in sentences]
words = set(itertools.chain(*sentences_lemmatized))
# set(['boy', 'fed', 'ate', 'cat', 'kicked', 'hat'])

# dictionaries for converting words to integers and vice versa
word2idx = dict((v, i) for i, v in enumerate(words))
idx2word = list(words)

# convert the sentences a numpy array
to_idx = lambda x: [word2idx[word] for word in x]
sentences_idx = [to_idx(sentence) for sentence in sentences_lemmatized]
sentences_array = np.asarray(sentences_idx, dtype='int32')

# parameters for the model
sentence_maxlen = 3
n_words = len(words)
n_embed_dims = 5

input_sentence = Input(shape=(sentence_maxlen,), dtype='int32')
input_embedding = Embedding(n_words, n_embed_dims)(input_sentence)
#color_prediction = SimpleRNN(init='uniform',output_dim=1,input_dim=3)(input_embedding)
#color_prediction = SimpleRNN(output_dim=1,input_dim=5,
 #       init='glorot_uniform', inner_init='orthogonal', activation='sigmoid', weights=None, return_sequences=False)(input_embedding);

color_prediction = SimpleRNN(3, return_sequences=False, batch_input_shape=(10, 2, 3))(input_embedding);
output = Dense(1, activation='sigmoid')(color_prediction)

predict_green = Model(input=[input_sentence], output=[output])
predict_green.compile(optimizer='sgd', loss='binary_crossentropy')

# fit the model to predict what color each person is
predict_green.fit([sentences_array], [is_green], nb_epoch=5000, verbose=1)
embeddings = predict_green.layers[1].W.get_value()

# print out the embedding vector associated with each word
for i in range(n_words):
    print('{}: {}'.format(idx2word[i], embeddings[i])) 

输出：

red: [-0.03866547 -0.04583547 -0.0314577  -0.04576075  0.00064603]
is: [-0.02093433 -0.00811194 -0.01167872 -0.02813761 -0.02160992]
bob: [-0.46798751 -0.01344876  0.36456427 -0.04407313  0.22842836]
sarah: [ 0.45210958  0.02854088 -0.34124625  0.0184452  -0.23039177]
green: [-0.00628944  0.04167764 -0.02662347 -0.01051781  0.03500782]
not: [-0.01113868 -0.01490347 -0.00235422 -0.03276222 -0.0263596 ]
sam: [ 0.45785579  0.04527023 -0.34266111 -0.01125967 -0.25254542]
hannah: [-0.45697126 -0.00369712  0.37587604 -0.04988953  0.23814654]