Combine keras functional api with tensorflow

Question

It's possible to combine tensorflow with keras sequential models like this: (source)

from keras.models import Sequential, Model

model = Sequential()
model.add(Dense(32, activation='relu', input_dim=784))
model.add(Dense(10, activation='softmax'))

# this works! 
x = tf.placeholder(tf.float32, shape=(None, 784))
y = model(x)

However, I want to use the functional API like this:

x = tf.placeholder(tf.float32, shape=(None, 784))
y = Dense(10)(x)
model = Model(inputs=x, outputs=y)

but when I try to do this, I get these errors:

TypeError: Input tensors to a Model must be Keras tensors. Found: Tensor("Placeholder_2:0", shape=(?, 784), dtype=float32) (missing Keras metadata).

Emil Johansson · Accepted Answer · 2019-09-14 09:48:58Z

1

The functional and seqential apis are two different ways to create a model object. But once that object you can treat them the same way. For example calling them whith tensorflow objects.

Here you can find documentation for the functional api

Here is a minimal example of using tensorflow tensors with the functional api.

import tensorflow as tf
from keras.layers import Input, Dense
from keras.models import Model

# Create the keras model.
inputs = Input(shape=(784,))
outputs = Dense(10)(inputs)
model = Model(inputs=inputs, outputs=outputs)

# Now that we have a model we can call it with x.
x = tf.placeholder(tf.float32, shape=(None, 784))
y = model(x)

answered Sep 14, 2019 at 9:48

Emil Johansson

3212 silver badges8 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

nuric · Accepted Answer · 2018-06-01 22:31:02Z

0

What you are looking for is the tensor argument of Input layer for the functional API.

tensor: Optional existing tensor to wrap into the Input layer. If set, the layer will not create a placeholder tensor.

answered Jun 1, 2018 at 22:31

nuric

11.3k3 gold badges29 silver badges43 bronze badges

1 Comment

lab_rat Over a year ago

Thank you for your help. Do you have an example that I could see? I tried this, but it didn't work. Sorry about the formatting. x = tf.placeholder(tf.float32, shape=(None, 784)) z = Input(tensor=x) pred = Dense(10)(x) model = Model(inputs=z, outputs=pred) model.compile(loss='mse',optimizer='sgd') a = model.predict(b_x) ValueError: ('Error when checking model : expected no data, but got:', array([[-0.21433205,

Collectives™ on Stack Overflow

Combine keras functional api with tensorflow

2 Answers 2

Comments

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related