You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Just noticing that "tf.keras.preprocessing" has been DEPRECIATED in tensor flow API.
For CNN videos in the course on UDEMY, models are still using ".image.ImageDataGenerator ", also for rescaling & DataAugmentation.
I used below available function for modelling CNN.
tf.keras.utils.image_dataset_from_directory(
train_dir,
label_mode="binary",
image_size=(224, 224),
batch_size=32,
)
model = tf.keras.Sequential([
data_augmentation,
tf.keras.layers.Rescaling(1./255),
Just Fyi in case any updates to be done on the online courses for future students.
Thank you
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
Just noticing that "tf.keras.preprocessing" has been DEPRECIATED in tensor flow API.
For CNN videos in the course on UDEMY, models are still using ".image.ImageDataGenerator ", also for rescaling & DataAugmentation.
I used below available function for modelling CNN.
tf.keras.utils.image_dataset_from_directory(
train_dir,
label_mode="binary",
image_size=(224, 224),
batch_size=32,
)
model = tf.keras.Sequential([
data_augmentation,
tf.keras.layers.Rescaling(1./255),
Just Fyi in case any updates to be done on the online courses for future students.
Thank you
Beta Was this translation helpful? Give feedback.
All reactions