qubvel / segmentation_models

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
MIT License
4.77k stars 1.03k forks source link

Support for Tensorflow 2.4 #440

Open lucas-langlois opened 3 years ago

lucas-langlois commented 3 years ago

Hi, I've just acquired a new machine with the lastest GPU RTX3090. This GPU is only supported for CUDA 11 meaning that I can only use the latest version of tensorflow (2.4). I know that for now segmentation-models only works for tensorflow 2.1. I would really like to use your library to do some semantic segmentation but it seems that I am stuck. Would you be able to estimate when tensorflow 2.4 support might be available ? Or any other ideas for me in the midtime ?

Thank you very much

pluniak commented 3 years ago

Are you sure it's not working? I'm using the repo with TF2.3.0.

lucas-langlois commented 3 years ago

Yeah I had it running fine previously. But now with Tensorflow 2.4.3 (the only one that would recognize the RTX3090) here are the error message I'm getting : 1) module 'keras.utils' has no attribute 'generic_utils' = found the way around that with %env SM_FRAMEWORK=tf.keras before loading segmentation-models 2) when training the model

ValueError Traceback (most recent call last)

in 1 # train model ----> 2 history = model.fit_generator( 3 train_dataloader, 4 steps_per_epoch=len(train_dataloader), 5 epochs=EPOCHS, ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch) 1845 'will be removed in a future version. ' 1846 'Please use `Model.fit`, which supports generators.') -> 1847 return self.fit( 1848 generator, 1849 steps_per_epoch=steps_per_epoch, ~\AppData\Local\R-MINI~1\envs\tensorflow24\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() ~\AppData\Local\R-MINI~1\envs\tensorflow24\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() ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds) 869 # This is the first call of __call__, so we have to initialize. 870 initializers = [] --> 871 self._initialize(args, kwds, add_initializers_to=initializers) 872 finally: 873 # At this point we know that the initialization is complete (or less ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to) 723 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph) 724 self._concrete_stateful_fn = ( --> 725 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access 726 *args, **kwds)) 727 ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs) 2967 args, kwargs = None, None 2968 with self._lock: -> 2969 graph_function, _ = self._maybe_define_function(args, kwargs) 2970 return graph_function 2971 ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs) 3359 3360 self._function_cache.missed.add(call_context_key) -> 3361 graph_function = self._create_graph_function(args, kwargs) 3362 self._function_cache.primary[cache_key] = graph_function 3363 ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 3194 arg_names = base_arg_names + missing_arg_names 3195 graph_function = ConcreteFunction( -> 3196 func_graph_module.func_graph_from_py_func( 3197 self._name, 3198 self._python_function, ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes) 988 _, original_func = tf_decorator.unwrap(python_func) 989 --> 990 func_outputs = python_func(*func_args, **func_kwargs) 991 992 # invariant: `func_outputs` contains only Tensors, CompositeTensors, ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds) 632 xla_context.Exit() 633 else: --> 634 out = weak_wrapped_fn().__wrapped__(*args, **kwds) 635 return out 636 ~\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs) 975 except Exception as e: # pylint:disable=broad-except 976 if hasattr(e, "ag_error_metadata"): --> 977 raise e.ag_error_metadata.to_exception(e) 978 else: 979 raise ValueError: in user code: C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function * return step_function(self, iterator) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function ** outputs = model.distribute_strategy.run(run_step, args=(data,)) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica return self._call_for_each_replica(fn, args, kwargs) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica return fn(*args, **kwargs) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step ** outputs = model.train_step(data) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\training.py:754 train_step y_pred = self(x, training=True) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__ input_spec.assert_input_compatibility(self.input_spec, inputs, self.name) C:\Users\jc238248\AppData\Local\R-MINI~1\envs\tensorflow24\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:204 assert_input_compatibility raise ValueError('Layer ' + layer_name + ' expects ' + ValueError: Layer model_3 expects 1 input(s), but it received 2 input tensors. Inputs received: [, ]
pluniak commented 3 years ago

Sorry, can't help you with that.

WeiChihChern commented 3 years ago

Can confirm this repo works with my 3090: a docker container in linux.

JordanMakesMaps commented 3 years ago

See #412 if you haven't already, it looks like it might be related?

lucas-langlois commented 3 years ago

Yes that was it! Works like a charm now. Thank you very much for the help. No chance I would have been able to debug that by myself.

Kritz23 commented 2 years ago

Yes that was it! Works like a charm now. Thank you very much for the help. No chance I would have been able to debug that by myself.

Hey, I tried the same approach its working fine, but I'm not able to use my GPU. Can you assist?

Thanks in advance!