Блог

Я пытаюсь обучаться трансферу с помощью MobileNetV3 в Керасе, но у меня возникли некоторые проблемы.

 from keras.models import Model
from keras.layers import GlobalMaxPooling2D, Dense, Dropout
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint
from tensorflow.keras.applications import MobileNetV3Small
import numpy as np
from tqdm import tqdm
from PIL import Image, ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

pretrained_model = MobileNetV3Small(input_shape=(224,224,3),
                                    weights="imagenet",
                                    include_top=False)

# freeze all layers except the last one
for layer in pretrained_model.layers:
    layer.trainable = False
pretrained_model.layers[-1].trainable = True

# combine the model with some extra layers for classification
last_output = pretrained_model.layers[-1].output
x = GlobalMaxPooling2D()(last_output)
x = Dense(128, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(1, activation='sigmoid')(x)
model = Model(pretrained_model.input, x)
 

Я получаю эту ошибку, когда пытаюсь сделать плотный слой:

 TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.
 

но это исправлено путем добавления следующего фрагмента кода:

 from tensorflow.python.framework.ops import disable_eager_execution
disable_eager_execution()
 

Когда я включаю исправление кода выше, я получаю эту ошибку при вызове model.fit() :

 FailedPreconditionError: 2 root error(s) found.
  (0) Failed precondition: Could not find variable Conv_1_2/kernel. This could mean that the variable has been deleted. In TF1, it can also mean the variable is uninitialized. Debug info: container=localhost, status=Not found: Resource localhost/Conv_1_2/kernel/N10tensorflow3VarE does not exist.
     [[{{node Conv_1_2/Conv2D/ReadVariableOp}}]]
     [[_arg_dense_12_target_0_1/_100]]
  (1) Failed precondition: Could not find variable Conv_1_2/kernel. This could mean that the variable has been deleted. In TF1, it can also mean the variable is uninitialized. Debug info: container=localhost, status=Not found: Resource localhost/Conv_1_2/kernel/N10tensorflow3VarE does not exist.
     [[{{node Conv_1_2/Conv2D/ReadVariableOp}}]]
0 successful operations.
0 derived errors ignored.
 

Как я могу устранить эти проблемы и обучить модель?

Из комментариев

Не смешивайте и не выделяйте . tf.keras keras Они несовместимы. Используйте только один из них (перефразировано из Frightera)

Рабочий код, как показано ниже

 from tensorflow.keras.models import Model
from tensorflow.keras.layers import GlobalMaxPooling2D, Dense, Dropout
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.applications import MobileNetV3Small
import numpy as np
from tqdm import tqdm
from PIL import Image, ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

pretrained_model = MobileNetV3Small(input_shape=(224,224,3),
                                    weights="imagenet",
                                    include_top=False)

# freeze all layers except the last one
for layer in pretrained_model.layers:
    layer.trainable = False
pretrained_model.layers[-1].trainable = True

# combine the model with some extra layers for classification
last_output = pretrained_model.layers[-1].output
x = GlobalMaxPooling2D()(last_output)
x = Dense(128, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(1, activation='sigmoid')(x)
model = Model(pretrained_model.input, x)