Cannot load .keras model

Question

I have trained a KERAS model (EfficientNetB5) on an image dataset, and have saved the new model with new layers into a .keras file. However, I keep getting an input error.

# Load efficientnet model without the top layer
efficientnetbasemodel = tf.keras.applications.EfficientNetB5(include_top=False,input_shape=(400, 400, 3))

# Freeze the base model layers
efficientnetbasemodel.trainable = False

#add new layers for training
name="efficientnet"
efficientnetmodel=tf.keras.Sequential([tf.keras.Input(shape=(None, None, 3), name="input_layer"),data_augmentation,efficientnetbasemodel,tf.keras.layers.GlobalAveragePooling2D(),
                                       tf.keras.layers.Dense(128, activation='relu'),tf.keras.layers.Dropout(0.2),tf.keras.layers.Dense(len(class_names), activation='softmax')], name=name)

# Compile the model
efficientnetmodel.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])

efficientnetmodel.fit(train_data,epochs=10,validation_data=val_data)

efficientnetmodel.save("efficientnetmodel.keras")

When I try to load the model again

from tensorflow.keras.models import load_model

# Load the model
model = load_model('efficientnetmodel.keras')

I get this error.

ValueError: Layer "dense_8" expects 1 input(s), but it received 2 input tensors. Inputs received: [<KerasTensor shape=(None, None, None, 2048), dtype=float32, sparse=False, name=keras_tensor_7687>, <KerasTensor shape=(None, None, None, 2048), dtype=float32, sparse=False, name=keras_tensor_7688>]" }

Bilal Arslan · Accepted Answer · 2024-07-30 10:32:44Z

3

This error is caused by a mismatch between the number of inputs expected by a layer in a Keras model and the number of inputs given to it. The dense_8 layer expects a single input, but it seems to have been given two inputs.

NOTE: This error may occur if two different inputs are given to the same layer anywhere in the above code.

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Dense

input_tensor = Input(shape=(None, None, 2048))
x = Dense(512, activation='relu')(input_tensor)
# There may be a case of accidentally using the same dense_8 
output_tensor = Dense(10, activation='softmax')(x)

model = Model(inputs=input_tensor, outputs=output_tensor)

answered Jul 30, 2024 at 10:32

Bilal Arslan

312 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Cannot load .keras model

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related