Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device

Hi I get this error from trying to use a tanh activation function in model.fit via keras. Any help would be much appreciated!

---------------------------------------------------------------------------

InternalError                             Traceback (most recent call last)

<timed exec> in <module>

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    886         # Lifting succeeded, so variables are initialized and we can run the
    887         # stateless function.
--> 888         return self._stateless_fn(*args, **kwds)
    889     else:
    890       _, _, _, filtered_flat_args = \

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
   2940       (graph_function,
   2941        filtered_flat_args) = self._maybe_define_function(args, kwargs)
-> 2942     return graph_function._call_flat(
   2943         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
   2944 

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1916         and executing_eagerly):
   1917       # No tape is watching; skip to running the function.
-> 1918       return self._build_call_outputs(self._inference_function.call(
   1919           ctx, args, cancellation_manager=cancellation_manager))
   1920     forward_backward = self._select_forward_and_backward_functions(

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
    553       with _InterpolateFunctionError(self):
    554         if cancellation_manager is None:
--> 555           outputs = execute.execute(
    556               str(self.signature.name),
    557               num_outputs=self._num_outputs,

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     57   try:
     58     ctx.ensure_initialized()
---> 59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
     60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:

InternalError:  Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device
	 [[node sequential/dense/Tanh (defined at <timed exec>:1) ]] [Op:__inference_train_function_559]

Function call stack:
train_function

nvidia-bug-report.log.gz (399.0 KB)