Keras Sequential Model

Creating the model | Specifying input size and batch size | specifying the activation function

Sequential Model : Linear stack of layers.

Create a Sequential Model by passing the layer instances to the constructor.

Import sequential model from Keras models.

from keras.models import Sequential

Import dense layer and activation function from keras layers 

from keras.layers import Dense, Activation


Create sequential model 

Input = can be of any dimension or a single element

Shape = length along each dimension of the input

Model needs to know the input shape it expects.

Only the first layer of the sequential model should know its input shape.

Batch = collection of inputs

Batch Size = no of inputs

• Create the model

          model = Sequential()

• Create the layer with batch size of 32 and input size of 784

          Dense(32,input_dim=784)

• Add the layer to the model

         model.add(Dense(32,input_dim=784))

• Add the activation function to the layer

          model.add(Activation('relu'))

Full Code

#import sequential model from keras models
from keras.models import Sequential
#import dense layer and activation function from karas layers
from keras.layers import Dense, Activation


#create sequential model
model = Sequential()

#add layer to the model
model.add(Dense(32, input_dim=784))

#add activation function to the layer
model.add(Activation('relu'))