Square brackets in keras model output shape - keras

Question

I've recently encountered this when looking at a model's summary.
I was wondering, what's the difference between [(None, 16)] and (None, 16)? Why does the Input layer have such input shape?
Source: model.summary() can't print output shape while using subclass model

Answer 1

The issue is how you are defining the input_shape. A single element tuple in python is actually a scalar value as you can see below -
input_shape0 = 32
input_shape1 = (32)
input_shape2 = (32,)
print(input_shape0, input_shape1, input_shape2)
32 32 (32,)
Since Keras function API Input needs an input shape as a tuple, you will have to pass it in the form of (n,) instead of n
It's weird that you get a square bracket because when I run the exact same code, I get an error.
TypeError Traceback (most recent call last)
<ipython-input-828-b564be68c80d> in <module>
33
34 if __name__ == '__main__':
---> 35 mlp = MLP((16))
36 mlp.summary()
<ipython-input-828-b564be68c80d> in __init__(self, input_shape, **kwargs)
6 super(MLP, self).__init__(**kwargs)
7 # Add input layer
----> 8 self.input_layer = klayers.Input(input_shape)
9
10 self.dense_1 = klayers.Dense(64, activation='relu')
~/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/input_layer.py in Input(shape, batch_size, name, dtype, sparse, tensor, **kwargs)
229 dtype=dtype,
230 sparse=sparse,
--> 231 input_tensor=tensor)
232 # Return tensor including `_keras_history`.
233 # Note that in this case train_output and test_output are the same pointer.
~/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/input_layer.py in __init__(self, input_shape, batch_size, dtype, input_tensor, sparse, name, **kwargs)
89 if input_tensor is None:
90 if input_shape is not None:
---> 91 batch_input_shape = (batch_size,) + tuple(input_shape)
92 else:
93 batch_input_shape = None
TypeError: 'int' object is not iterable
Therefore, the right way to do it (which should fix your model summary as well is as below -
from tensorflow import keras
from tensorflow.keras import layers as klayers
class MLP(keras.Model):
def __init__(self, input_shape=(32,), **kwargs):
super(MLP, self).__init__(**kwargs)
# Add input layer
self.input_layer = klayers.Input(input_shape)
self.dense_1 = klayers.Dense(64, activation='relu')
self.dense_2 = klayers.Dense(10)
# Get output layer with `call` method
self.out = self.call(self.input_layer)
# Reinitial
super(MLP, self).__init__(
inputs=self.input_layer,
outputs=self.out,
**kwargs)
def build(self):
# Initialize the graph
self._is_graph_network = True
self._init_graph_network(
inputs=self.input_layer,
outputs=self.out
)
def call(self, inputs):
x = self.dense_1(inputs)
return self.dense_2(x)
if __name__ == '__main__':
mlp = MLP((16,))
mlp.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_19 (InputLayer) (None, 16) 0
_________________________________________________________________
dense_8 (Dense) (None, 64) 1088
_________________________________________________________________
dense_9 (Dense) (None, 10) 650
=================================================================
Total params: 1,738
Trainable params: 1,738
Non-trainable params: 0
_________________________________________________________________