1. keras.engine.input_layer.Input()
| def Input(shape=None, batch_shape=None, | |
| name=None, dtype=None, sparse=False, | |
| tensor=None): |
Used to instantiate a keras tensor
2. class Dense(Layer):
keras.layers.Dense(units, activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)
| def __init__(self, units, | |
| activation=None, | |
| use_bias=True, | |
| kernel_initializer='glorot_uniform', | |
| bias_initializer='zeros', | |
| kernel_regularizer=None, | |
| bias_regularizer=None, | |
| activity_regularizer=None, | |
| kernel_constraint=None, | |
| bias_constraint=None, | |
| ** kwargs): |
Dense is a class for regular densely-connected NN layer.
3. from keras.models import Sequential, Model
4. from keras.utils.np_utils import to_categorical
categorical_labels = to_categorical(int_labels, num_classes=None)
Description:
For example, if you have 10 categories, labels of each sample should be a 10-dimensional vector, the vector corresponding to the index value is 1 the rest position is 0.
EXAMPLE：
Android.permission.FACTOR. Assumed vector 100x1 and 100 represents the number of samples, a scalar tag, label this time expanded to 10-dimensional vector, namely: y_test is 100x10.10 dimensional vector, the value of 1 indicates that the sample belongs to this category, another 9 value places are zero.
y_test = to_categorical(y_test, 10)