How can I solve "Failed copying input tensor" issue?

Question

While executing the code:

I get the following error:

InternalError: Failed copying input tensor from /job:localhost/replica:0/task:0/device:CPU:0 to /job:localhost/replica:0/task:0/device:GPU:0 in order to run _EagerConst: Dst tensor is not initialized.

I am trying to evaluate model. Fitting process:

# Fit the model DenseNet with Augmented data
epochs = 50
batch_size = 64
history = model.fit_generator(datagen.flow(x_train_aug,y_train_aug, batch_size=batch_size),
                              epochs = epochs, validation_data = (x_validate_aug,y_validate_aug),
                              verbose = 1, steps_per_epoch=x_train_aug.shape[0] // batch_size
                              , callbacks=[learning_rate_reduction])

Can anyone help me to solve this issue?