概念
搭建神經(jīng)網(wǎng)絡(luò)塊是一種常見的做法，它可以幫助你更好地組織和復(fù)用網(wǎng)絡(luò)結(jié)構(gòu)。神經(jīng)網(wǎng)絡(luò)塊可以是一些相對獨(dú)立的模塊，例如卷積塊、全連接塊等，用于構(gòu)建更復(fù)雜的網(wǎng)絡(luò)架構(gòu)。文章來源地址http://www.zghlxwxcb.cn/news/detail-655551.html
代碼實(shí)現(xiàn)
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
# 定義一個卷積塊
def convolutional_block(x, num_filters, kernel_size, pool_size):
x = layers.Conv2D(num_filters, kernel_size, activation='relu', padding='same')(x)
x = layers.MaxPooling2D(pool_size)(x)
return x
# 構(gòu)建神經(jīng)網(wǎng)絡(luò)模型
def build_model():
inputs = layers.Input(shape=(28, 28, 1)) # 輸入數(shù)據(jù)為28x28的灰度圖像
x = convolutional_block(inputs, num_filters=32, kernel_size=(3, 3), pool_size=(2, 2))
x = convolutional_block(x, num_filters=64, kernel_size=(3, 3), pool_size=(2, 2))
x = layers.Flatten()(x)
x = layers.Dense(128, activation='relu')(x)
outputs = layers.Dense(10, activation='softmax')(x) # 輸出層，10個類別
model = keras.Model(inputs, outputs)
return model
# 加載數(shù)據(jù)
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = np.expand_dims(x_train, axis=-1).astype('float32') / 255.0
x_test = np.expand_dims(x_test, axis=-1).astype('float32') / 255.0
y_train = keras.utils.to_categorical(y_train, num_classes=10)
y_test = keras.utils.to_categorical(y_test, num_classes=10)
# 構(gòu)建模型
model = build_model()
# 編譯模型
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# 訓(xùn)練模型
model.fit(x_train, y_train, batch_size=64, epochs=10, validation_split=0.1)
# 評估模型
test_loss, test_accuracy = model.evaluate(x_test, y_test)
print("Test Loss:", test_loss)
print("Test Accuracy:", test_accuracy)
文章來源：http://www.zghlxwxcb.cn/news/detail-655551.html
到了這里，關(guān)于神經(jīng)網(wǎng)絡(luò)基礎(chǔ)-神經(jīng)網(wǎng)絡(luò)補(bǔ)充概念-30-搭建神經(jīng)網(wǎng)絡(luò)塊的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
