Tensorflow API, Tensorflow hub and Keras input shape

Question

I am working with tf=2.0.0, and tensorflow hub. Currently I am using the Tensorflow data API to load my data which is stored in a tfrecords file.

I am successfully loading the dataset and compiling the model but when I try to fit the data into the model I get the error:

Error when checking input: expected inputs_input to have 1 dimensions, but got array with shape (64, 1)

This is how I am loading my data:

def _dataset_parser(value):
    """Parse a record from value."""
    featdef={
        'id':  tf.io.FixedLenFeature([1], tf.int64),
        'question': tf.io.FixedLenFeature([1], tf.string),
        'label': tf.io.FixedLenFeature([1], tf.int64)
    }

    example = tf.io.parse_single_example(value, featdef)

    label = tf.cast(example['label'], tf.int32)
    question = tf.cast(example['question'], tf.string)
    return example['question'], example['label']
def _input(epochs, batch_size, filenames):
    dataset = tf.data.TFRecordDataset(filenames)

    dataset = dataset.repeat(epochs)
    dataset = dataset.prefetch(1)

    # Parse records.
    dataset = dataset.map(_dataset_parser)
    dataset = dataset.shuffle(100)

    # Batch it up.
    dataset = dataset.batch(batch_size)
    iterator = tf.compat.v1.data.make_one_shot_iterator(dataset)

    question_batch, label_batch = iterator.get_next()
    label_batch = tf.one_hot(label_batch, NUM_CLASSES)

    return question_batch, label_batch



train_ds = _input(20, 64, ['train_xs.tfrecords'])

This is my model:

model = tf.keras.Sequential([
        hub.KerasLayer(HUB_URL, dtype=tf.string, input_shape=[], output_shape=[WIDTH], name='inputs'),
        tf.keras.layers.Dense(256, 'relu', name ='layer_1'),
        tf.keras.layers.Dense(128, 'relu', name = 'layer_2'),
        tf.keras.layers.Dense(NUM_CLASSES, activation='softmax', name='output')
    ])

    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=["accuracy"])

I already tried setting the input shape of the entry layer as (None, 1) but it keeps failing, not sure if the problem is due to TensorFlow hub however I tried running this example from the hands-on-ml book:

model = tf.keras.Sequential([
    hub.KerasLayer("https://tfhub.dev/google/tf2-preview/nnlm-en-dim50/1",
                   dtype=tf.string, input_shape=[], output_shape=[50]),
    tf.keras.layers.Dense(128, activation="relu"),
    tf.keras.layers.Dense(1, activation="sigmoid")
])
model.compile(loss="binary_crossentropy", optimizer="adam",
              metrics=["accuracy"])
datasets, info = tfds.load("imdb_reviews", as_supervised=True, with_info=True)
train_size = info.splits["train"].num_examples
batch_size = 32
train_set = datasets["train"].repeat().batch(batch_size).prefetch(1)
history = model.fit(train_set, steps_per_epoch=5, epochs=5)#steps_per_epoch=train_size // batch_size, epochs=5)

and it works fine, however one difference I found is that if I print the train_set on the example from the book I get:

<PrefetchDataset shapes: ((None,), (None,)), types: (tf.string, tf.int64)>

Whereas with my code I get this when I print the dataset that I am feeding to the model:

(<tf.Tensor: id=11409, shape=(64, 1), dtype=string, numpy=  array([[b'Restroom score out of 9'],
        [b'Name'],
        [b'Lastname'],
        [b'Type of house'],
        [b'Inspection date'],
        [b'Pet'],
        [b'Phone'], dtype=object)>,  <tf.Tensor: id=11414, shape=(64, 1, 80), dtype=float32, numpy=  array([[[0., 0., 0., ...,
0., 0., 0.]],

        [[0., 0., 0., ..., 0., 0., 0.]],

        [[0., 0., 0., ..., 0., 0., 0.]],

        ...,

        [[0., 0., 0., ..., 0., 0., 0.]],

        [[0., 0., 0., ..., 0., 0., 0.]],

        [[0., 0., 0., ..., 0., 0., 0.]]], dtype=float32)>)

Does someone know why the difference in the shape of the data?

Answer 1

If anyone is interested, this is the final code that worked for me:

    model = tf.keras.Sequential([
        hub.KerasLayer(HUB_URL, dtype=tf.string, input_shape=[], output_shape=[WIDTH], name='inputs'),
name=INPUT_TENSOR_NAME),
        tf.keras.layers.Dense(256, 'relu', name ='layer_1'),
        tf.keras.layers.Dense(128, 'relu', name = 'layer_2'),
        tf.keras.layers.Dense(NUM_CLASSES, activation='softmax', name='output')
    ])

    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=["accuracy"])

    def _dataset_parser(value):
        """Parse a record from value."""
        featdef={
            'id':  tf.io.FixedLenFeature([], tf.int64),
            'question': tf.io.FixedLenFeature([], tf.string),
            'label': tf.io.FixedLenFeature([], tf.int64)
        }

        example = tf.io.parse_single_example(value, featdef)

        label = tf.cast(example['label'], tf.int64)
        question = tf.cast(example['question'], tf.string)
        return question, tf.one_hot(label, NUM_CLASSES)

    def _input(epochs, batch_size, filenames):
        dataset = tf.data.TFRecordDataset(filenames)

        dataset = dataset.repeat(epochs)
        dataset = dataset.prefetch(1)

        # Parse records.
        dataset = dataset.map(_dataset_parser)
        dataset = dataset.shuffle(100)

        # Batch it up.
        dataset = dataset.batch(batch_size)


        return dataset

    train_ds = _input(1, 10, ['train_xs.tfrecords'])

    model.fit(train_ds,epochs=1)

Answer 2

Not sure why, but by changing the feature definition to

 featdef={
        'id':  tf.io.FixedLenFeature([], tf.int64),
        'question': tf.io.FixedLenFeature([], tf.string),
        'label': tf.io.FixedLenFeature([], tf.int64)
    }

it worked