Home > Back-end >  Keras sequential model from functional API
Keras sequential model from functional API

Time:12-19

I have a Keras model using functional API and it looks:

nn = keras.layers.Conv1D(300,19,strides=1,activation='relu')(inputs) 
nn = keras.layers.Conv1D(300,19,strides=1,activation='relu')(nn) 

nn = keras.layers.MaxPool1D(pool_size=3)(nn)

nn = keras.layers.Flatten()(nn)
nn = keras.layers.Dense(596,activation='relu')(nn)

logits = keras.layers.Dense(35, activation='linear')(nn)
outputs = keras.layers.Activation('sigmoid')(logits)

I want to convert it to sequential model however I am confused how logit and output layer would look like in sequential model. So what I have so far:

model.add(keras.layers.Conv1D(300,19,'relu',input_shape=dataset['x_train'].shape[1:])
model.add(keras.layers.Conv1D(300,19,'relu')
model.add(Flatten())
model.add(keras.layers.Dense(596,'relu'))

I am confused about the next two layers. Can someone guide me how to code for it in a sequential model. Help will be much appreciated.

CodePudding user response:

You can use tf.keras.Model and pass inputs, outputs and get the model.summary() and create an exact model with tf.keras.Sequential() like the below: (You can see the Total params: 3,706,091 for both of models.)

Using functional API:

import tensorflow as tf
inputs = tf.keras.layers.Input((64, 64))
nn = tf.keras.layers.Conv1D(300,19,strides=1,activation='relu')(inputs) 
nn = tf.keras.layers.Conv1D(300,19,strides=1,activation='relu')(nn) 
nn = tf.keras.layers.MaxPool1D(pool_size=3)(nn)
nn = tf.keras.layers.Flatten()(nn)
nn = tf.keras.layers.Dense(596,activation='relu')(nn)
logits = tf.keras.layers.Dense(35, activation='linear')(nn)
outputs = tf.keras.layers.Activation('sigmoid')(logits)
model = tf.keras.Model(inputs, outputs)
model.summary()

Output:

Model: "model_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_2 (InputLayer)        [(None, 64, 64)]          0         
                                                                 
 conv1d_2 (Conv1D)           (None, 46, 300)           365100    
                                                                 
 conv1d_3 (Conv1D)           (None, 28, 300)           1710300   
                                                                 
 max_pooling1d_1 (MaxPooling  (None, 9, 300)           0         
 1D)                                                             
                                                                 
 flatten_1 (Flatten)         (None, 2700)              0         
                                                                 
 dense_2 (Dense)             (None, 596)               1609796   
                                                                 
 dense_3 (Dense)             (None, 35)                20895     
                                                                 
 activation_1 (Activation)   (None, 35)                0         
                                                                 
=================================================================
Total params: 3,706,091
Trainable params: 3,706,091
Non-trainable params: 0
_________________________________________________________________

Create an exact model with tf.keras.Sequential().

import tensorflow as tf
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(300,19,strides=1,activation='relu',input_shape=(64,64)))
model.add(tf.keras.layers.Conv1D(300,19,strides=1,activation='relu'))
model.add(tf.keras.layers.MaxPool1D(pool_size=3))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(596,'relu'))
model.add(tf.keras.layers.Dense(35, activation='linear'))
model.add(tf.keras.layers.Activation('sigmoid'))
model.summary()

Output:

Model: "sequential_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv1d_2 (Conv1D)           (None, 46, 300)           365100    
                                                                 
 conv1d_3 (Conv1D)           (None, 28, 300)           1710300   
                                                                 
 max_pooling1d_1 (MaxPooling  (None, 9, 300)           0         
 1D)                                                             
                                                                 
 flatten_1 (Flatten)         (None, 2700)              0         
                                                                 
 dense_2 (Dense)             (None, 596)               1609796   
                                                                 
 dense_3 (Dense)             (None, 35)                20895     
                                                                 
 activation_1 (Activation)   (None, 35)                0         
                                                                 
=================================================================
Total params: 3,706,091
Trainable params: 3,706,091
Non-trainable params: 0
_________________________________________________________________
  • Related