我是神经网络的新手。我的代码下面一行出现错误
net = tflearn.input_data(shape=[None, len(train_x[0])])
下面是错误,我正在得到”
TypeError: object of type 'numpy.float64' has no len()
我尝试使用以下语法,但仍然给我一个错误
net = tflearn.input_data(shape=[None, len(train_x)])
我得到的错误:
ValueError: Cannot feed value of shape (8,) for Tensor 'InputData/X:0', which has shape '(?, 19579)'
您能帮我建议怎么办吗?
此外,如果需要,下面是完整的语法
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
# Input data files are available in the "../input/" directory.
# Any results you write to the current directory are saved as output.
#from subprocess import check_output
#print(check_output(["ls", "../input"]).decode("utf8"))
train = pd.read_csv('C:/Users/gunjit.bedi/Desktop/Tensor Flow/input/train.csv')
print(train.head())
import nltk as nl
train['tokens'] = [nl.word_tokenize(sentences) for sentences in train.text]
words = []
for item in train.tokens:
words.extend(item)
stemmer = nl.stem.lancaster.LancasterStemmer()
words = [stemmer.stem(word) for word in words]
filtered_words = [word for word in words if word not in nl.corpus.stopwords.words('english')]
import gensim
# let X be a list of tokenized texts (i.e. list of lists of tokens)
model = gensim.models.Word2Vec(filtered_words, size=100)
w2v = dict(zip(model.wv.index2word, model.wv.syn0))
print(w2v['h'])
training = []
for index, item in train.iterrows():
vec = np.zeros(100)
token_words = [stemmer.stem(word) for word in item['tokens']]
token_words = [word for word in token_words if word not in nl.corpus.stopwords.words('english')]
for w in token_words:
if w in w2v:
vec += w2v[w]
norm = np.linalg.norm(vec)
if norm != 0:
vec /= np.linalg.norm(vec)
training.append(vec)
training_new = np.array(training)
from numpy import array
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
# integer encode
label_encoder = LabelEncoder()
integer_encoded = label_encoder.fit_transform(training_new[:,1])
# binary encode
onehot_encoder = OneHotEncoder(sparse=False)
integer_encoded = integer_encoded.reshape(len(integer_encoded), 1)
onehot_encoded = onehot_encoder.fit_transform(integer_encoded)
train_y = onehot_encoded
train_x = list(training_new[:,0])
print(len(train_x))
print(type(train_x))
import tensorflow as tf
import tflearn
# reset underlying graph data
tf.reset_default_graph()
# Build neural network
net = tflearn.input_data(shape=[None, len(train_x[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(train_y), activation='softmax')
net = tflearn.regression(net)
# Define model and setup tensorboard
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')
# Start training (apply gradient descent algorithm)
model.fit(train_x, train_y, n_epoch=10, batch_size=8, show_metric=True)
model.save('model.tflearn')
答案 0 :(得分:0)
len()
告诉您传递给它的数组的长度。
train_x[0]
为您提供train_x
数组的 first 元素,该元素没有任何length属性,因此会出现错误消息。
TypeError: object of type 'numpy.float64' has no len()
这就是为什么删除[0]
时不会从len(train_x)
收到错误。
我对Tensor Flow并不熟悉,因此无法进一步评论,但这有望解释您的错误原因。
答案 1 :(得分:0)
我能够解决以上问题,以下代码似乎出现了错误
training = []
for index, item in train.iterrows():
vec = np.zeros(100)
token_words = [stemmer.stem(word) for word in item['tokens']]
token_words = [word for word in token_words if word not in nl.corpus.stopwords.words('english')]
for w in token_words:
if w in w2v:
vec += w2v[w]
norm = np.linalg.norm(vec)
if norm != 0:
vec /= np.linalg.norm(vec)
training.append(vec)
我将其更改为以下内容:检查代码的最后一行
training = []
for index, item in train.iterrows():
vec = np.zeros(100)
token_words = [stemmer.stem(word) for word in item['tokens']]
token_words = [word for word in token_words if word not in nl.corpus.stopwords.words('english')]
for w in token_words:
if w in w2v:
vec += w2v[w]
norm = np.linalg.norm(vec)
if norm != 0:
vec /= np.linalg.norm(vec)
training.append([vec,item['author']])
该错误是因为未附加“作者”列。 如果tensorflow专家可以确认我的解决方案是否正确,那将是很好的选择。