https://tensorflow.google.cn/tutorials/keras/text_classification

解決方案

import tensorflow as tf from tensorflow import kerasimport numpy as npprint(tf.__version__) imdb = keras.datasets.imdb(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000) print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels))) print(train_data[0]) print(len(train_data[0]), len(train_data[1])) # 一個映射單詞到整數(shù)索引的詞典 word_index = imdb.get_word_index()# 保留第一個索引 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>"] = 3reverse_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])print(decode_review(train_data[0]))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)print(len(train_data[0]), len(train_data[1]))print(train_data[0])# 輸入形狀是用于電影評論的詞匯數(shù)目（10,000 詞） vocab_size = 10000model = keras.Sequential() model.add(keras.layers.Embedding(vocab_size, 16)) model.add(keras.layers.GlobalAveragePooling1D()) model.add(keras.layers.Dense(16, activation='relu')) model.add(keras.layers.Dense(1, activation='sigmoid'))model.summary()model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])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, verbose=2)print(results)history_dict = history.history print(history_dict.keys())import matplotlib.pyplot as pltacc = history_dict['accuracy'] val_acc = history_dict['val_accuracy'] loss = history_dict['loss'] val_loss = history_dict['val_loss']epochs = range(1, len(acc) + 1)# “bo”代表 "藍(lán)點(diǎn)" plt.plot(epochs, loss, 'bo', label='Training loss') # b代表“藍(lán)色實(shí)線” plt.plot(epochs, val_loss, 'b', label='Validation loss') plt.title('Training and validation loss') plt.xlabel('Epochs') plt.ylabel('Loss') plt.legend()plt.show()plt.clf() # 清除數(shù)字plt.plot(epochs, acc, 'bo', label='Training acc') plt.plot(epochs, val_acc, 'b', label='Validation acc') plt.title('Training and validation accuracy') plt.xlabel('Epochs') plt.ylabel('Accuracy') plt.legend()plt.show()

參考文章

?

總結(jié)

以上是生活随笔為你收集整理的TensorFlow 教程——电影评论文本分类的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。