0
$\begingroup$

I'm trying to do a superresolution network, but I am having trouble importing my own data. I have two types of images: resized images (smaller), original images. The first one is going to be used as an input of the network and the second ones will be used for training the network.

The problem is that the only examples that I see about ImageDataGenerator are used for classification problems, so I don't know how import this two different datasets of images.

I tried

train_small_datagen = ImageDataGenerator(rescale=1./255)
train_normal_datagen = ImageDataGenerator(rescale=1./255)

train_small_generator = train_small_datagen.flow_from_directory(
   train_small_path,
   target_size= (300, 300),
   batch_size=20,
)

train_normal_generator = train_normal_datagen.flow_from_directory(
   train_normal_path,
   target_size=(150,150),
   batch_size=20,
)
model.fit_generator(x=train_small_generator, y=train_normal_generator,
         epochs=500,
         batch_size=30,  # 30
         validation_steps=4,
         steps_per_epoch=20,
         validation_batch_size=20,
         validation_split=0.2,
         callbacks=[tensorboard])

I know that it doesn't work that way but I don't know how to make it work.

$\endgroup$

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.