I am using ASUS TUF FX516-AZ042,python3.7, tensorflow 2.4.1, cuda 11.2.2 , geforce rtx 3060(laptop). When I run the fashion image dataset for my Deepleaning for transfer learning by tensorflow gpu, in training process show me error. Even I use cuda 11.3 , same error. And there is no transfer learning, ok. The problem is only on transfer learning.
I tried this code in another computer, it will work well.
NotFoundError Traceback (most recent call last)
in
5 batch_size=32,
6 validation_data = (validation_img, validation_labe),
----> 7 callbacks = callbacks
8 )
~\anaconda3\envs\tensorflow\lib\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\envs\tensorflow\lib\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\envs\tensorflow\lib\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\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in call (self, *args, **kwargs)
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
2945 @property
~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
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(
1921 args,
~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
558 inputs=args,
559 attrs=attrs,
→ 560 ctx=ctx)
561 else:
562 outputs = execute.execute_with_cancellation(
~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
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:
62 if name is not None:
NotFoundError: No algorithm worked!
[[node sequential/vgg19/block1_conv1/Relu (defined at :7) ]] [Op:__inference_train_function_1631]
Function call stack:
train_function
Any Idea for how to solve this?