R ValueError: Error when checking input: expected simple_rnn_input to have 3 dimensions, but got array with shape (1661, 3)

Question

这是我的代码：

used_time_period = "2009-01-01::2017-04-01"

data_used = data_input[used_time_period,]

split_coefficient = 0.8

train_set_rate = round(nrow(data_used) * split_coefficient)

data_train = data_used[1:train_set_rate,]

data_test = data_used[(train_set_rate + 1):nrow(data_used),]

model = keras_model_sequential() %>%

layer_simple_rnn(units = 75, input_shape = dim(data_train[,1:3]), activation = "relu", return_sequences = TRUE) %>% 
layer_dense(units = 2, activation = "relu")

model %>% compile(optimizer = "adam", loss = "binary_crossentropy", metrics = "binary_accuracy")

history = model %>% fit(x = data_train[,1:3], y = data_train[,4:5], epochs = 40, batch_size = 20)

我得到的错误是：

ValueError: Error when checking input: expected simple_rnn_input to have 3 dimensions, but got array with shape (1661, 3)

dim(data_train[,1:3]) = (1661, 3)

dim(data_train[,4:5]) = (1661, 2)

我做错了什么？

Answer 1

如错误消息所述，layer_simple_rnn 需要 3D 数组，但您使用的是 data.frame，这是一个 2D 数组（具有行和列的 table）。

根据 Keras documentation，循环层需要一个形状为 (batch_size, timesteps, input_dim) 的数组。假设每一列对应不同的日期（如果我错了请纠正我），这应该可以工作：

dim(data_train[, 1:3]) # [1] 10  3
X <- as.matrix(data_train[, 1:3]) # Convert to an array
dim(X) # [1] 10  3

dim(X) <- c(dim(X), 1)
dim(X) # [1] 10  3  1

# The same for Y
Y <- as.matrix(data_train[, 4:5])
dim(Y) <- c(dim(Y), 1)

现在 X 和 Y 有 3 个维度，您可以将它们提供给您的模型：

history = model %>% fit(x = X, y = Y, epochs = 40, batch_size = 20)

R ValueError: Error when checking input: expected simple_rnn_input to have 3 dimensions, but got array with shape (1661, 3)

R ValueError: Error when checking input: expected simple_rnn_input to have 3 dimensions, but got array with shape (1661, 3)

r

machine-learning

deep-learning

keras

keras-layer