search

CityUHK-CompBio / DeepCC

DeepCC: a novel deep learning-based framework for cancer molecular subtype classification
https://CityUHK-CompBio.github.io/DeepCC/
MIT License
20 stars 16 forks source link

Shapes used to initialize variables must be fully-defined (no None dimensions). #19

Open RadulDev opened 1 month ago

RadulDev commented 1 month ago

I was trying the tool with the given model, but came across this error. can any one help me guide me through using this tools correctly.

Error: Shapes used to initialize variables must be fully-defined (no None dimensions). Received: shape=(None,) for variable path='sequential/batch_normalization/gamma'Traceback:

  1. load_DeepCC_model("/home/dell/BRC_TCGA")
  2. keras::load_model_hdf5(filepath = paste0(prefix, ".hdf5"))
  3. load_model(filepath, custom_objects, compile)
  4. do.call(keras$models$load_model, args)
  5. (structure(function (filepath, custom_objects = NULL, compile = TRUE, . safe_mode = TRUE) . { . cl <- sys.call() . cl[[1L]] <- list2 . call_args <- split_named_unnamed(eval(cl, parent.frame())) . result <- py_call_impl(callable, call_args$unnamed, call_args$named) . if (py_get_convert(callable)) . result <- py_to_r(result) . if (is.null(result)) . invisible(result) . else result . }, class = c("python.builtin.function", "python.builtin.object" . ), py_object = ))(filepath = "/home/dell/BRC_TCGA.hdf5", . custom_objects = NULL, compile = TRUE)
  6. py_call_impl(callable, call_args$unnamed, call_args$named)