CODEWITHSUNDEEP
tensorflowkerastraining-datavgg-net
Rstynbl
Rstynbl

Reputation: 575

FailedPreconditionError: Attempting to use uninitialized value Adam/lr

I was on the process of training a VGG16 fine-tuned model.After the first epoch,the program stopped and gave this error:

Screenshot of the error on jupyter notebook

Below is the code I used for the model:

# create a copy of a mobilenet model
import keras
vgg_model=keras.applications.vgg16.VGG16()

type(vgg_model)

vgg_model.summary()

from keras.models import Sequential
model = Sequential()
for layer in vgg_model.layers[:-1]:
    model.add(layer)

model.summary()

# CREATE THE MODEL ARCHITECTURE
from keras.layers import Dense, Activation, Dropout

model.add(Dropout(0.25))
model.add(Dense(7,activation='softmax'))

model.summary()

#Train the Model
# Define Top2 and Top3 Accuracy

from keras.metrics import categorical_accuracy, top_k_categorical_accuracy

def top_3_accuracy(y_true, y_pred):
    return top_k_categorical_accuracy(y_true, y_pred, k=3)

def top_2_accuracy(y_true, y_pred):
    return top_k_categorical_accuracy(y_true, y_pred, k=2)

from keras.optimizers import Adam
model.compile(Adam(lr=0.01), loss='categorical_crossentropy', 
              metrics=[categorical_accuracy, top_2_accuracy, top_3_accuracy])

# Get the labels that are associated with each index
print(valid_batches.class_indices)

# Add weights to try to make the model more sensitive to melanoma

class_weights={
    0: 1.0, # akiec
    1: 1.0, # bcc
    2: 1.0, # bkl
    3: 1.0, # df
    4: 3.0, # mel # Try to make the model more sensitive to Melanoma.
    5: 1.0, # nv
    6: 1.0, # vasc
}

filepath = "skin.h5"
checkpoint = ModelCheckpoint(filepath, monitor='val_top_3_accuracy', verbose=1, 
                             save_best_only=True, mode='max')

reduce_lr = ReduceLROnPlateau(monitor='val_top_3_accuracy', factor=0.5, patience=2, 
                                   verbose=1, mode='max', min_lr=0.00001)
                              
                              
callbacks_list = [checkpoint, reduce_lr]

history = model.fit_generator(train_batches, steps_per_epoch=train_steps, 
                              class_weight=class_weights,
                    validation_data=valid_batches,
                    validation_steps=val_steps,
                    epochs=40, verbose=1,
                   callbacks=callbacks_list)

I am trying to learn how to fine tune, train and use VGG16 model on image dataset. I was following this blog where he used mobileNet.

I was following this VGG16 tutorial to write the code for the model.

If anyone can help me fix this error or explain how and why it happened I would highly appreciate your help.

Dependencies:

Upvotes: 3

Views: 1080

Answers (1)

kielnino
kielnino

Reputation: 180

I had the same error when I used the ReduceLROnPlateau callback. Unless it's absolutely necessary, you can maybe omit its usage.

Upvotes: 3

Related Questions