Tensorflow2中如何提高多核CPU的利用率

Question

我在windows上用的是tensorflow2，CPU的利用率极低，所以我查了一下任务管理器，发现只有ONE CORE Working

然后我在网上搜索在我的代码前面添加以下代码，没有区别

tf.config.threading.set_intra_op_parallelism_threads(48) tf.config.threading.set_inter_op_parallelism_threads(48)

我该如何修复它。以下是我的代码

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import *

tf.config.threading.set_intra_op_parallelism_threads(48)
tf.config.threading.set_inter_op_parallelism_threads(48)

def build_model(layer1=10, layer2=10):

    model = keras.Sequential()

    model.add(Dense(layer1, kernel_initializer='he_normal', input_shape=[11]))
    model.add(Dense(layer2, kernel_initializer='he_normal'))

    model.add(Dense(10, kernel_initializer='he_normal', activation='softmax'))

    optimizer = keras.optimizers.Adam(learning_rate=0.0015)
    model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer=optimizer)

    return model

model = built_model()
model.fit(x, y)