基于tensorflow的模型预测与评估

# 准备数据建立模型训练模型预测(测试) 评估模型。# 1.准备数据(train_x, train_y), (test_x, test_y) = imdb.load_data(num_words=10000)t1 = Tokenizer(num_words=10000)t1.fit_on_sequences(train_x)train_x = t1.sequences_to_matrix(train_x)test_x = t1.sequences_to_matrix(test_x)# 2.建立模型model = Sequential()model.add(Dense(units=32, activation="relu", input_shape=(25000, 10000)))model.add(Dense(units=32, activation="relu"))model.add(Dense(units=1, activation="sigmoid"))model.compile(optimizer="rmsprop", loss="binary_crossentropy", metrics=["accuracy"])# 3.训练model.fit(x=train_x, y=train_y, batch_size=256, epochs=5)# 4.预测result = model.predict(x=test_x, batch_size=256)# 5.评估score = model.evaluate(test_x, test_y)print("预测的结果:", result)print("真实的答案:", test_y)print("考试得分:", score)