Я работаю над проблемой классификации OVA (один против всех). Для этого я обучил бинарные классификаторы Keras с сигмовидной функцией и binary_crossentropy. Мне нужно объединить их в мультиклассовую модель, аналогичную здесь Когда я пытаюсь это сделать, я получаю следующую ошибку
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'sequential_input' with dtype float and shape [?,224,224,3]
[[{{node sequential_input}}]]
Программный код
for i in os.listdir(model_root): //loading all the models
print(i)
filename = model_root + "/" + i
# load model
model = load_model(filename, custom_objects={'KerasLayer': hub.KerasLayer})
models.append(model)
print(len(models)) //3
#Merge layer to fit a model
inputs = tf.keras.Input(shape=(224,224,3))
outputs = [m(inputs) for m in models]
outputs = tf.keras.layers.concatenate(outputs, axis=-1)
ensemble = tf.keras.models.Model(inputs, outputs)
ensemble.compile(optimizer=tf.keras.optimizers.Adam(), loss='categorical_crossentropy', metrics=['accuracy'])
#To fit the loaded models to the data
steps_per_epoch = image_data.samples // image_data.batch_size
validation_steps = image_data_val.samples / image_data_val.batch_size
ensemble.fit((item for item in image_data), epochs=2,
steps_per_epoch=steps_per_epoch,
validation_data=(item for item in image_data_val), validation_steps=validation_steps, verbose=2)
Я получаю эту ошибку в функции подгонки. Вот трассировка
Epoch 1/2
Traceback (most recent call last):
File "<input>", line 1, in <module>
File "C:\Program Files\JetBrains\PyCharm 2019.2\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "C:\Program Files\JetBrains\PyCharm 2019.2\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/Users/Pawandeep/Desktop/Python projects/ensemble_image.py", line 85, in <module>
validation_data=(item for item in image_data_val), validation_steps=validation_steps, verbose=2)
File "C:\Python\lib\site-packages\tensorflow\python\keras\engine\training.py", line 673, in fit
initial_epoch=initial_epoch)
File "C:\Python\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1433, in fit_generator
steps_name='steps_per_epoch')
File "C:\Python\lib\site-packages\tensorflow\python\keras\engine\training_generator.py", line 264, in model_iteration
batch_outs = batch_function(*batch_data)
File "C:\Python\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1175, in train_on_batch
outputs = self.train_function(ins) # pylint: disable=not-callable
File "C:\Python\lib\site-packages\tensorflow\python\keras\backend.py", line 3292, in __call__
run_metadata=self.run_metadata)
File "C:\Python\lib\site-packages\tensorflow\python\client\session.py", line 1458, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'dense_1_target' with dtype float and shape [?,?]
[[{{node dense_1_target}}]]
Моя модель выглядит так
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3) 0
__________________________________________________________________________________________________
sequential_4 (Sequential) (None, 1) 3541267 input_1[0][0]
__________________________________________________________________________________________________
sequential_8 (Sequential) (None, 1) 3541267 input_1[0][0]
__________________________________________________________________________________________________
sequential_2 (Sequential) (None, 1) 3541267 input_1[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 3) 0 sequential_4[1][0]
sequential_8[1][0]
sequential_2[1][0]
==================================================================================================
Total params: 10,623,801
Trainable params: 3,006
Non-trainable params: 10,620,795
__________________________________________________________________________________________________
Я не могу найти тензор плотности
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'sequential_input' with dtype float and shape [?,224,224,3]
[[{{node sequential_input}}]]
Мои данные выглядят так:
image_data = image_generator.flow_from_directory(str(data_root), target_size=IMAGE_SIZE, subset='training')
for image_batch, label_batch in image_data:
print("Image batch shape: ", image_batch.shape) // (32, 224, 224, 3)
print("Label batch shape: ", label_batch.shape) // (32, 3)
Теперь, где я могу разместить заполнители и как я могу связать их со своими входными данными.
