我想获得矢量大小（46）。但我得到了数组。我使用的数据集是路透社。我打印 NN 预测的地方是代码的最后几行。代码：from keras.datasets import reutersfrom keras import models, layers, lossesfrom keras.utils.np_utils import to_categoricalimport numpy as np(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)word_index = reuters.get_word_index()reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])decoded_newswire = ' '.join([reverse_word_index.get(i - 3, '?') for i in train_data[0]])def vectorize_sequences(sequences, dimension=10000): results = np.zeros((len(sequences), dimension)) for i, equences in enumerate(sequences): results[i, sequences] = 1. return resultsx_train = vectorize_sequences(train_data)x_test = vectorize_sequences(test_data)one_hot_train_labels = to_categorical(train_labels)one_hot_test_labels = to_categorical(test_labels)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='adam', 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=9, batch_size=128, validation_data=(x_val, y_val))predictions = model.predict(x_test)predictions[0].shapeprint(predictions)输出：# WHY? [[4.2501447e-06 1.9825067e-07 2.3206076e-07 ... 2.1613120e-07 9.8317461e-09 1.3596014e-07] [1.6055314e-02 1.4951903e-01 1.4057434e-04 ... 1.1199807e-04 1.8230558e-06 2.4111385e-03] [7.8554759e-03 6.6994888e-01 1.6705523e-03 ... 4.0704478e-04 2.4865860e-05 7.2334736e-04] ...
添加回答
举报
0/150
提交
取消