[英]Error in Keras network on IMDB dataset example. Incompatible shapes
我相信我已经正确矢量化了训练和测试数据、标签、足够的层、合适的优化器,但我不明白哪里出了问题。 为什么我会收到不兼容形状的 ValueError?
我的代码:
from keras.datasets import imdb
(train_data, train_labels),(test_data, test_labels)=imdb.load_data(num_words=10000)
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
def to_one_hot(labels, dimension=46):
results = np.zeros((len(labels), dimension))
for i, label in enumerate(labels):
results[i, label] = 1.
return results
one_hot_train_labels = to_one_hot(train_labels)
one_hot_test_labels = to_one_hot(test_labels)
from tensorflow.keras.utils import to_categorical
one_hot_train_labels = to_categorical(train_labels)
one_hot_test_labels = to_categorical(test_labels)
from keras import models
from keras import layers
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(46, activation='softmax'))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
x_val = x_train[:1000]
partial_x_train = x_train[1000:]
y_val = one_hot_train_labels[:1000]
partial_y_train = one_hot_train_labels[1000:]
history = model.fit(partial_x_train, partial_y_train, epochs=20, batch_size=512, validation_data=(x_val, y_val)
我的错误信息:
ValueError:形状(无,1)和(无,46)不兼容
根据评论,如果您的partial_y_train
形状是 (24000, 1) 那么这意味着它没有被正确地热编码。 您在代码中使用 function to_one_hot()
,但我不知道这段代码在做什么。 最好使用 Tensorflow 的one_hot
function或scikit-learn的版本,然后形状应该匹配并且错误将被删除。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.