specifying input shape in keras model in object-oriented way

Question

Compare the following code snippets. I implemented a simple keras model like this

inp = layers.Input((10,2))
x = layers.Flatten()(inp)
x = layers.Dense(5)(x)
m = models.Model(inputs=inp, outputs=x)

For one reason or another, I need to have my model in an objective way. So no problem, it's easy to reimplement that into:

class MyModel(tf.keras.Model):
   def __init__(self, inp_shape, out_size = 5):
       super(MyModel, self).__init__()
       self.inp = layers.InputLayer(input_shape=inp_shape)
       self.flatten = layers.Flatten()
       self.dense = layers.Dense(out_size)

   def call(self, a):
       x = self.inp(a)
       x = self.flatten(x)
       x = self.dense(x)
       return x

However in the second case when I try to run:

m = MyModel((10,2))
m.summary()

I get:

ValueError: This model has not yet been built. Build the model first by calling `build()` or calling `fit()` with some data, or specify an `input_shape` argument in the first layer(s) for automatic build.

I don't quite get why? Shouldn't the above be equivalent?

Abhishek Prajapat · Accepted Answer · 2021-07-13 23:12:52Z

1

The reason for this is that when you create an object of this model you are just creating its layers and not its graph. So in short the output from layer 1 is not going in layer 2 cause those are entirely separate attributes of the class but when you call the model those separate attributes combines and form the graph.

answered Jul 13, 2021 at 23:12

Abhishek Prajapat

1,8882 gold badges11 silver badges20 bronze badges

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

Comments

Innat · Accepted Answer · 2021-07-13 17:09:34Z

0

When you define a model in tf. keras with subclassed API, you need to build the model first by calling build or run the model on some data.

m = MyModel((10,2))
m.build(input_shape=(10, 2)) # < -- build the model 
m.summary()

That said, you don't also need to define self.inp while building the model with subclassed API. The .summary() may not look right to you for the subclassed model, you may need to check this instead.

answered Jul 13, 2021 at 17:09

Innat

17.3k6 gold badges60 silver badges115 bronze badges

7 Comments

A. Newski Over a year ago

Isn't that a bit repetitive, as I define input already here: MyModel((10,2)) ?

Innat Over a year ago

Not exactly. Building model in seq and func API are like data structure whereas in subclass API is simply a piece of python code. That’s why Input layer or a specification layer only part of the non-subclassed api model.

Innat Over a year ago

You shouldn’t or don't need to define the spec layer inside subclassed api model.

A. Newski Over a year ago

Which one is spec layer?

A. Newski Over a year ago

BTW the whole point of me trying to print the summary was to see if the output shapes match, however here I get: output shape "multiple", which does not match functional API summary that correctly printed Dense output shape as 5.

|

Collectives™ on Stack Overflow

specifying input shape in keras model in object-oriented way

2 Answers 2

Comments

7 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

7 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related