machine-learning - Keras TypeError : Cannot convert Type TensorType(float32, 3D)(变量子张量{:int64:}. 0)

Question

下面的代码片段给了我一些tensorType错误

TypeError:无法将类型 TensorType(float32, 3D)(Variable 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

我是机器学习新手，也遇到了你的问题。我按如下方式更改了代码并运行了，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]