ValueError: in user code while using keras model in R

I am trying to run 1 dimensional CNN in R using keras package. I am using the following code

library(MASS)
library(keras)

##Create some data
data("Boston")
data <- Boston
# create a list of 70% of the rows in the original dataset we can use for training
set.seed(123)
training <- sample(nrow(data), 0.7 * nrow(data))

dataTrain <- data[training,]
dataTest <- data[-training,]

dataTrain_y <- as.matrix(dataTrain$medv)
dataTrain_x <- as.matrix(subset(dataTrain, select = -c(medv)))

dataTest_y <- as.matrix(dataTest$medv)
dataTest_x <- as.matrix(subset(dataTest, select = -c(medv)))

#Reshaping the data for CNN
dataTrain_x <- array_reshape(dataTrain_x, c(ncol(dataTrain_x), nrow(dataTrain_x), 1))
dataTest_x <- array_reshape(dataTest_x, c(ncol(dataTest_x), nrow(dataTest_x), 1))

#CNN model
model <- keras_model_sequential() %>%
  layer_conv_1d(filters=32, kernel_size=4, activation="relu", 
                input_shape=c(ncol(dataTrain_x), nrow(dataTrain_x))) %>%
  layer_max_pooling_1d(pool_size=2) %>%
  layer_conv_1d(filters=64, kernel_size=2, activation="relu") %>%
  layer_max_pooling_1d(pool_size=2) %>%
  layer_dropout(rate=0.4) %>%
  layer_flatten() %>%
  layer_dense(units=100, activation="relu") %>%
  layer_dropout(rate=0.2) %>%
  layer_dense(units=1, activation="linear")

model %>% compile(
  loss = "mse",
  optimizer =  "adam", #'sgd' can also be used
  metrics = list("mean_absolute_error")
)

model %>% summary()

history <- model %>% fit(dataTrain_x, dataTrain_y, 
                         epochs = 100, batch_size = 50, 
                         #callbacks = callback_tensorboard("logs/run_a"),
                         validation_split = 0.2)

But it returns me the following error

Error in py_call_impl(callable, dots$args, dots$keywords) : 
  ValueError: in user code:
    C:\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function  *
        return step_function(self, iterator)
    C:\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:\Python37\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step  **
        outputs = model.train_step(data)
    C:\Python37\lib\site-pac

Now how can I solve this error?

Solution

The error message is truncated, so it's not much help, but it looks to me like you've got some minor typos. If you make the suggested changes (the "###" comments) the model appears to compile and train as expected, e.g.

library(MASS)
library(keras)

##Create some data
data("Boston")
data <- Boston
# create a list of 70% of the rows in the original dataset we can use for training
set.seed(123)
training <- sample(nrow(data), 0.7 * nrow(data))

dataTrain <- data[training,]
dataTest <- data[-training,]

dataTrain_y <- as.matrix(dataTrain$medv)
dataTrain_x <- as.matrix(subset(dataTrain, select = -c(medv)))

dataTest_y <- as.matrix(dataTest$medv)
dataTest_x <- as.matrix(subset(dataTest, select = -c(medv)))

#Reshaping the data for CNN
### These dimensions don't look correct; switch ncol() with nrow()
dataTrain_x <- array_reshape(dataTrain_x, c(nrow(dataTrain_x), ncol(dataTrain_x), 1))
dataTest_x <- array_reshape(dataTest_x, c(nrow(dataTest_x), ncol(dataTest_x), 1))

#CNN model
model <- keras_model_sequential() %>%
  layer_conv_1d(filters=32, kernel_size=4, activation="relu", 
                ### The input shape doesn't look correct; instead of 
                ### `c(ncol(dataTrain_x), nrow(dataTrain_x))` (354, 13)
                ### I believe you want `dim(dataTest_x)` (13, 1)
                input_shape=c(ncol(dataTrain_x), 1)) %>%
  layer_max_pooling_1d(pool_size=2) %>%
  layer_conv_1d(filters=64, kernel_size=2, activation="relu") %>%
  layer_max_pooling_1d(pool_size=2) %>%
  layer_dropout(rate=0.4) %>%
  layer_flatten() %>%
  layer_dense(units=100, activation="relu") %>%
  layer_dropout(rate=0.2) %>%
  layer_dense(units=1, activation="linear")

model %>% compile(
  loss = "mse",
  optimizer =  "adam", #'sgd' can also be used
  metrics = list("mean_absolute_error")
)

model %>% summary()
#> Model: "sequential"
#> ________________________________________________________________________________
#> Layer (type)                        Output Shape                    Param #     
#> ================================================================================
#> conv1d_1 (Conv1D)                   (None, 10, 32)                  160         
#> ________________________________________________________________________________
#> max_pooling1d_1 (MaxPooling1D)      (None, 5, 32)                   0           
#> ________________________________________________________________________________
#> conv1d (Conv1D)                     (None, 4, 64)                   4160        
#> ________________________________________________________________________________
#> max_pooling1d (MaxPooling1D)        (None, 2, 64)                   0           
#> ________________________________________________________________________________
#> dropout_1 (Dropout)                 (None, 2, 64)                   0           
#> ________________________________________________________________________________
#> flatten (Flatten)                   (None, 128)                     0           
#> ________________________________________________________________________________
#> dense_1 (Dense)                     (None, 100)                     12900       
#> ________________________________________________________________________________
#> dropout (Dropout)                   (None, 100)                     0           
#> ________________________________________________________________________________
#> dense (Dense)                       (None, 1)                       101         
#> ================================================================================
#> Total params: 17,321
#> Trainable params: 17,321
#> Non-trainable params: 0
#> ________________________________________________________________________________

history <- model %>% fit(dataTrain_x, dataTrain_y, 
                         epochs = 100, batch_size = 50, 
                         #callbacks = callback_tensorboard("logs/run_a"),
                         validation_split = 0.2)

^{Created on 2021-07-20 by the reprex package (v2.0.0)}