如何使用顺序Keras模型和多处理并行进行预测？

import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import multi_gpu_model
from keras.utils import np_utils
from keras.models import load_model
from keras import backend as K
import tensorflow as tf

model = Sequential()
model.add(Dense(64, input_dim=100, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.load_weights('model_weights.h5')

def predict(data):
    with tf.device('/cpu:0'):
        predictions = model.predict(data)
    return predictions

num_processes = 4  # 设置并行处理的进程数
data = np.random.random((1000, 100))  # 输入数据
data_splits = np.array_split(data, num_processes)  # 将数据划分为多个子集

import multiprocessing

pool = multiprocessing.Pool(processes=num_processes)
results = pool.map(predict, data_splits)
pool.close()
pool.join()

predictions = np.concatenate(results)
print(predictions)