daily pastebin goal
24%
SHARE
TWEET

Untitled

a guest Mar 22nd, 2019 63 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. # partition the data into training and testing splits using 75% of
  2. # the data for training and the remaining 25% for testing
  3. (trainX, testX, trainY, testY) = train_test_split(data,
  4.     labels, test_size=0.25, random_state=42)
  5. print ("trainX.shape------>>",trainX.shape)
  6. # convert the labels from integers to vectors (for 2-class, binary
  7. # classification you should use Keras' to_categorical function
  8. # instead as the scikit-learn's LabelBinarizer will not return a
  9. # vector)
  10. lb = LabelBinarizer()
  11. trainY = lb.fit_transform(trainY)
  12. testY = lb.transform(testY)
  13.  
  14. # construct the image generator for data augmentation
  15. aug = ImageDataGenerator(rotation_range=30, width_shift_range=0.1,
  16.     height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
  17.     horizontal_flip=True, fill_mode="nearest")
  18.  
  19. height = 64
  20. width = 64
  21. depth =3
  22.  
  23. inputShape = (height, width, depth)
  24.  
  25. classes = len(lb.classes_)
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy. OK, I Understand
 
Top