# DEFINE THE LSTM MODEL
    #input_shape <- c(52.0, 5.0)
    #input_shape = c(seq_length, ncol(close_data))
    #layer_input(shape = input_shape) %>%

    model <- keras_model_sequential() %>%
      layer_lstm(units = 50, return_sequences = TRUE, 
             input_shape = c(52, 5)) %>%
      layer_lstm(units = 50) %>%
      layer_dense(units = 1)

the code above keeps yielding this error:

Error in py_call_impl(callable, call_args$unnamed, call_args$named) : 
  ValueError: Only input tensors may be passed as positional arguments. The following argument value should be passed as a keyword argument: <Sequential name=sequential_1, built=False> (of type <class 'keras.src.models.sequential.Sequential'>)

if you notice, I tried to do ‘input_shape’ in multiple different ways, as shown by the comments at the start.

This is my first time working with neural networks and I have no idea whats going wrong. For reference, I want to use a timestep of 52, and I have 5 features. I’ve modified the code in many other ways that yielded way too many errors to put in one post. I’ve also configured, re-configured, re-installed, and completely changed the python environment that I was using. (I started off using a virtual environment with ‘r-reticulate’ and eventually switched to a conda env(with all the right dependencies installed.

ANY guidance would be appreciated.

I put all of the stuff in this section in the section above. sorry its also my first time using stack overflow.