this is code I used
#prepare labels
labelsPostive=numpy.ones((postiveImgNumbers,),dtype=int)
labelsNegative=numpy.zeros((negativeImgNumbers,),dtype=int)
labels=numpy.concatenate((labelsPostive,labelsNegative))
but this gave me an error:"
Exception: You are passing a target array of shape (11438, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:
```
from keras.utils.np_utils import to_categorical
y_binary = to_categorical(y_int)"
I have only one class (my problem is binary classification )and do not need to use "to_categorical(y_int)"
use this instruction in Keras
from keras.utils import np_utils
Y_train = np_utils.to_categorical(y_train, nb_classes)
- Badges
- Science topic
- Similar topics
- Data Mining
- Classification