卷积神经网络的R语言代码

以下是一个简单的卷积神经网络的R语言代码示例：

library(keras)

# 设置模型参数
batch_size <- 128
num_classes <- 10
epochs <- 12

# 输入图像维度
img_rows <- 28
img_cols <- 28

# 加载 MNIST 数据集
mnist <- dataset_mnist()
x_train <- mnist$train$x
y_train <- mnist$train$y
x_test <- mnist$test$x
y_test <- mnist$test$y

# 数据预处理
x_train <- array_reshape(x_train, c(nrow(x_train), img_rows, img_cols, 1))
x_test <- array_reshape(x_test, c(nrow(x_test), img_rows, img_cols, 1))
x_train <- x_train / 255
x_test <- x_test / 255
y_train <- to_categorical(y_train, num_classes)
y_test <- to_categorical(y_test, num_classes)

# 定义模型
model <- keras_model_sequential() %>%
  layer_conv_2d(filters = 32, kernel_size = c(3, 3), activation = "relu", 
                input_shape = c(img_rows, img_cols, 1)) %>%
  layer_conv_2d(filters = 64, kernel_size = c(3, 3), activation = "relu") %>%
  layer_max_pooling_2d(pool_size = c(2, 2)) %>%
  layer_dropout(rate = 0.25) %>%
  layer_flatten() %>%
  layer_dense(units = 128, activation = "relu") %>%
  layer_dropout(rate = 0.5) %>%
  layer_dense(units = num_classes, activation = "softmax")

# 编译模型
model %>% compile(
  loss = "categorical_crossentropy",
  optimizer = optimizer_adadelta(),
  metrics = c("accuracy")
)

# 训练模型
model %>% fit(
  x_train, y_train,
  batch_size = batch_size,
  epochs = epochs,
  verbose = 1,
  validation_data = list(x_test, y_test)
)

# 评估模型
score <- model %>% evaluate(x_test, y_test, verbose = 0)
cat("Test loss:", score[[1]], "\n")
cat("Test accuracy:", score[[2]], "\n")

这个模型使用了两个卷积层和一个最大池化层来提取图像的特征，然后使用两个全连接层来进行分类。在训练过程中，我们使用了 Adadelta 优化器和交叉熵损失函数来最小化模型的误差，并且使用了 Dropout 技术来防止过拟合。最终，我们得到了一个在 MNIST 数据集上达到了 99% 的准确率的模型。