Saya melakukan klasifikasi teks menggunakan jaringan saraf dalam dengan keras mengikuti tutorial, tetapi ketika saya menjalankan kode berikut beberapa kali, saya mendapatkan hasil yang berbeda.
Misalnya, kerugian pengujian pada putaran pertama adalah 0,88815, dan pada putaran kedua adalah 0,89030 yang berarti sedikit lebih tinggi. Saya bertanya-tanya dari mana datangnya keacakan itu?
import keras
from keras.datasets import reuters
(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=None, test_split=0.2)
word_index = reuters.get_word_index(path="reuters_word_index.json")
print('# of Training Samples: {}'.format(len(x_train)))
print('# of Test Samples: {}'.format(len(x_test)))
num_classes = max(y_train) + 1
print('# of Classes: {}'.format(num_classes))
index_to_word = {}
for key, value in word_index.items():
index_to_word[value] = key
print(' '.join([index_to_word[x] for x in x_train[0]]))
print(y_train[0])
from keras.preprocessing.text import Tokenizer
max_words = 10000
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print(x_train[0])
print(len(x_train[0]))
print(y_train[0])
print(len(y_train[0]))
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.metrics_names)
batch_size = 32
epochs = 3
history = model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_split=0.1)
score = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
