Array as input for tensorflow

Question

I am trying to use an array as an input for a tensorflow model The training input is xs The training output is ys The input to test is zs When i train the model everything works fine but if i use predict this error appears:

ValueError                                Traceback (most recent call last)
<ipython-input-1-08c8b5d5ab9e> in <module>()
     26 model.fit(xs,ys, epochs=500)
     27 
---> 28 print(model.predict(zs))
     29 #print(str(model.get_weights()))
     30 #np.array([np.array(x) for x in xs])

10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1462 predict_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1452 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1445 run_step  **
        outputs = model.predict_step(data)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1418 predict_step
        return self(x, training=False)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py:976 __call__
        self.name)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py:216 assert_input_compatibility
        ' but received input with shape ' + str(shape))

    ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 3 but received input with shape [None, 1]

This is my code:

import numpy as np
from tensorflow import keras

model = tf.keras.Sequential([keras.layers.Dense(units=3, input_shape=[3])])
model.add(keras.layers.Dense(units=20))
model.add(keras.layers.Dense(units=40))
model.add(keras.layers.Dense(units=100))
model.add(keras.layers.Dense(units=20))
model.add(keras.layers.Dense(units=1))

#model.set_weights()
model.compile(optimizer='sgd', loss='mean_squared_error')

xs = tf.constant([[15,0,0],
               [17,0,0],
               [19,1,0],
               [21,1,20],
               [23,1,20],
               [1,1,0],
               [3,1,0],
               [5,1,0]])
ys = tf.constant([0,0,0,0,0,1,1,1])
zs = tf.constant([15,0,0])
print(model.output_shape)
model.fit(xs,ys, epochs=500)

print(model.predict(zs))

How can I use my model correcly? I heard about evealuate but this just returns the loss.

Lescurel · Accepted Answer · 2020-12-15 16:32:57Z

1

A Keras input expects a batch dimension. Your zs variable does not have it.

You can use zs = tf.expand_dims(zs,axis=0) to add the batch dimension, or use a nested list when creating zs.

zs = tf.constant([[15,0,0]])

You can check the shape expected by the model by looking at its inputs:

>>> model.input.shape
TensorShape([None, 3])

Here None, means that the first dimension can be any number > 0.

If you check your variable zs, you will see that the shape does not match.

>>> zs = tf.constant([15,0,0])
>>> zs.shape
TensorShape([3])

But if we use tf.expand_dims, or use a nested list when constructing zs, the shape will be compatible.

>>> zs_exp = tf.expand_dims(zs,axis=0)
>>> zs_exp.shape
TensorShape([1, 3])
>>> zs_nested_list = tf.constant([[15,0,0]])
>>> zs_nested_list.shape
TensorShape([1, 3])

edited Dec 15, 2020 at 16:32

answered Dec 15, 2020 at 16:25

Lescurel

11.7k21 silver badges43 bronze badges

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

Comments

Dinesh Nagumothu · Accepted Answer · 2020-12-15 16:34:51Z

1

Change your input to something like this

zs = tf.constant([[15,0,0]])

The shape of prediction input should be similar to training input

answered Dec 15, 2020 at 16:34

Dinesh Nagumothu

1221 silver badge3 bronze badges

Collectives™ on Stack Overflow

Array as input for tensorflow

2 Answers 2

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related