#machine-learning #deep-learning #computer-vision #conv-neural-network
Вопрос:
Я должен реализовать Conv3D на последовательности изображений. В файле 72 изображения, и размер каждого изображения равен (16,16,3), где 3-канал. Ниже приведен мой код:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.layers import Conv3D, MaxPooling3D
from tensorflow.keras.utils import to_categorical
input_shape = (7,16,16,3) # 7 is the no. of images to be input to Conv3D at a time.
no_classes = 1
epoch = 7
verbosity = 1
learning_rate = 0.001
model = Sequential()
model.add(Conv3D(5,kernel_size=(3, 3, 3),padding ='same',activation='relu',kernel_initializer='he_uniform',input_shape=input_shape))
model.add(MaxPooling3D(pool_size=(2, 2, 3), padding= 'same'))
model.add(Conv3D(3,kernel_size=(3, 3, 3),padding='same',activation='relu',kernel_initializer='he_uniform'))
model.add(MaxPooling3D(pool_size=(2, 2, 2), padding = 'same'))
model.add(Flatten())
model.add(Dense(256, activation='relu', kernel_initializer='he_uniform'))
model.add(Dense(no_classes, activation='softmax'))
model.compile(loss=tf.keras.losses.categorical_crossentropy,
optimizer=tf.keras.optimizers.Adam(lr=learning_rate),
metrics=['accuracy'])
model.summary()
# Fit data to model
history = model.fit(trainX, new_trainy,
batch_size = 25,
epochs = 7)
Я получаю следующую ошибку:
Epoch 1/7
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-47-92321d5fc5a8> in <module>()
2 history = model.fit(trainX, new_trainy,
3 batch_size = batch_size,
----> 4 epochs = epoch)
9 frames
/usr/local/lib/python3.7/dist-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()
/usr/local/lib/python3.7/dist-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()
/usr/local/lib/python3.7/dist-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
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self,
args, kwds, add_initializers_to)
724 self._concrete_stateful_fn = (
725 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint:
disable=protected-access
--> 726 *args, **kwds))
727
728 def invalid_creator_scope(*unused_args, **unused_kwds):
/usr/local/lib/python3.7/dist-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
/usr/local/lib/python3.7/dist-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
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in
_create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3204 arg_names=arg_names,
3205 override_flat_arg_shapes=override_flat_arg_shapes,
-> 3206 capture_by_value=self._capture_by_value),
3207 self._function_attributes,
3208 function_spec=self.function_spec,
/usr/local/lib/python3.7/dist-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,
/usr/local/lib/python3.7/dist-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
/usr/local/lib/python3.7/dist-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:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:754 train_step
y_pred = self(x, training=True)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py:998 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py:239 assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=5, found ndim=4. Full shape received: (None, 16, 16, 3)
trainX имеет форму (72,16,16,3), где 72-количество изображений, (16,16) — размер изображения, а 3-канал, т. е. rgb
Может ли кто-нибудь, пожалуйста, помочь мне выйти из этой ошибки. Любая помощь была бы весьма ощутима.
Ответ №1:
Я действительно попал туда, где совершаю ошибку:
Каждый ввод в Conv3D должен быть 4-мерной точкой данных. В то время как в моем случае каждая точка данных в наборе данных, т. е. trainX, имеет форму(16,16,3), которая является 3-мерной. Чтобы каждая точка данных имела одинаковую форму, т. е. 4D(7,16,16,3), я удалил последние 2 изображения из trainX, чтобы количество изображений или точек данных (т. Е. 70) в trainX было кратно 7. Затем я изменил данные trainX на 5D.
Теперь в trainX есть 10 точек данных, в которых каждая точка данных равна 4D (т. е. (7,16,16,3)).
Это устранило ошибку, и моя модель была выполнена идеально. Ниже приведен код:
new_trainX = trainX[:70,:,:,:]
new_trainX2 = tf.reshape(new_trainX,shape = (10,7,16,16,3))
# Fit data to model
history = model.fit(new_trainX2, new_trainy,
batch_size = batch_size,
epochs = epoch)
Here is the output:
Epoch 1/7
1/1 [==============================] - 1s 557ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 2/7
1/1 [==============================] - 0s 129ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 3/7
1/1 [==============================] - 0s 131ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 4/7
1/1 [==============================] - 0s 129ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 5/7
1/1 [==============================] - 0s 128ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 6/7
1/1 [==============================] - 0s 140ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Epoch 7/7
1/1 [==============================] - 0s 129ms/step - loss: 0.0000e 00 - accuracy: 1.0000
Надеюсь, это будет полезно.