Logo Questions Linux Laravel Mysql Ubuntu Git Menu
HTML CSS JAVASCRIPT SQL PYTHON PHP BOOTSTRAP JAVA JQUERY R React Kotlin
 

Tensorflow model.fit() using a Dataset generator

Tags:

python

tensorflow

tensorflow2.0

tensorflow-datasets

tf.keras

I am using the Dataset API to generate training data and sort it into batches for a NN.

Here is a minimum working example of my code:

import tensorflow as tf
import numpy as np
import random


def my_generator():
    while True:
        x = np.random.rand(4, 20)
        y = random.randint(0, 11)
        label = tf.one_hot(y, depth=12)
        yield x.reshape(4, 20, 1), label

def my_input_fn():
    dataset = tf.data.Dataset.from_generator(lambda: my_generator(),
                                             output_types=(tf.float64, tf.int32))

    dataset = dataset.batch(32)
    iterator = dataset.make_one_shot_iterator()
    batch_features, batch_labels = iterator.get_next()

    return batch_features, batch_labels


if __name__ == "__main__":
    tf.enable_eager_execution()

    model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
                                 tf.keras.layers.Dense(128, activation=tf.nn.relu),
                                 tf.keras.layers.Dense(12, activation=tf.nn.softmax)])

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

    data_generator = my_input_fn()
    model.fit(data_generator)

The code fails using TensorFlow 1.13.1 at the model.fit() call with the following error:

Traceback (most recent call last):
  File "scripts/min_working_example.py", line 37, in <module>
    model.fit(data_generator)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 880, in fit
    validation_steps=validation_steps)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_arrays.py", line 310, in model_iteration
    ins_batch = slice_arrays(ins[:-1], batch_ids) + [ins[-1]]
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 526, in slice_arrays
    return [None if x is None else x[start] for x in arrays]
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 526, in <listcomp>
    return [None if x is None else x[start] for x in arrays]
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 654, in _slice_helper
    name=name)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 820, in strided_slice
    shrink_axis_mask=shrink_axis_mask)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 9334, in strided_slice
    _six.raise_from(_core._status_to_exception(e.code, message), None)
  File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError: Attr shrink_axis_mask has value 4294967295 out of range for an int32 [Op:StridedSlice] name: strided_slice/

I tried running the same code on a different machine using TensorFlow 2.0 (after removing the line tf.enable_eager_execution() because it runs eagerly by default) and I got the following error:

Traceback (most recent call last):
  File "scripts/min_working_example.py", line 37, in <module>
    model.fit(data_generator)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 873, in fit
    steps_name='steps_per_epoch')
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_arrays.py", line 352, in model_iteration
    batch_outs = f(ins_batch)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3217, in __call__
    outputs = self._graph_fn(*converted_inputs)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 558, in __call__
    return self._call_flat(args)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 627, in _call_flat
    outputs = self._inference_function.call(ctx, args)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 397, in call
    (len(args), len(list(self.signature.input_arg))))
ValueError: Arguments and signature arguments do not match: 21 23

I tried changing model.fit() to model.fit_generator() but this fails on both TensorFlow versions too. On TF 1.13.1 I get the following error:

Traceback (most recent call last):
  File "scripts/min_working_example.py", line 37, in <module>
    model.fit_generator(data_generator)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1426, in fit_generator
    initial_epoch=initial_epoch)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 115, in model_iteration
    shuffle=shuffle)
  File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 377, in convert_to_generator_like
    num_samples = int(nest.flatten(data)[0].shape[0])
TypeError: __int__ returned non-int (type NoneType)

and on TF 2.0 I get the following error:

Traceback (most recent call last):
  File "scripts/min_working_example.py", line 37, in <module>
    model.fit_generator(data_generator)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 1515, in fit_generator
    steps_name='steps_per_epoch')
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 140, in model_iteration
    shuffle=shuffle)
  File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 477, in convert_to_generator_like
    raise ValueError('You must specify `batch_size`')
ValueError: You must specify `batch_size`

yet batch_size is not a recognized keyword for fit_generator().

I am puzzled by these error messages and I would appreciate if anyone can shed some light on them, or point out what I am doing wrong.

like image 654
berkelem Avatar asked Mar 27 '19 10:03

berkelem

People also ask

How do you fit a model in TensorFlow?

When you need to customize what fit() does, you should override the training step function of the Model class. This is the function that is called by fit() for every batch of data. You will then be able to call fit() as usual -- and it will be running your own learning algorithm.

What does model fit () do?

What is Model Fitting? Model fitting is a measure of how well a machine learning model generalizes to similar data to that on which it was trained. A model that is well-fitted produces more accurate outcomes.

What is model fit () in Python?

model. fit() : fit training data. For supervised learning applications, this accepts two arguments: the data X and the labels y (e.g. model. fit(X, y) ). For unsupervised learning applications, this accepts only a single argument, the data X (e.g. model.

What method is used to fit a model on batches from an ImageDataGenerator?

You can do this by calling the fit() function on the data generator and passing it to your training dataset. The data generator itself is, in fact, an iterator, returning batches of image samples when requested.

1 Answers

While the origin of the errors is still nebulous, I have found a solution that makes the code work. I'll post it here in case it is useful to anyone in a similar situation.

Basically, I changed the my_input_fn() into a generator and used model.fit_generator() as follows:

import tensorflow as tf
import numpy as np
import random


def my_generator(total_items):
    i = 0
    while i < total_items:
        x = np.random.rand(4, 20)
        y = random.randint(0, 11)
        label = tf.one_hot(y, depth=12)
        yield x.reshape(4, 20, 1), label
        i += 1

def my_input_fn(total_items, epochs):
    dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
                                             output_types=(tf.float64, tf.int64))

    dataset = dataset.repeat(epochs)
    dataset = dataset.batch(32)


    iterator = dataset.make_one_shot_iterator()
    while True:
        batch_features, batch_labels = iterator.get_next()
        yield batch_features, batch_labels

if __name__ == "__main__":
    tf.enable_eager_execution()

    model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
                                 tf.keras.layers.Dense(64, activation=tf.nn.relu),
                                 tf.keras.layers.Dense(12, activation=tf.nn.softmax)])

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

    total_items = 200
    batch_size = 32
    epochs = 10
    num_batches = int(total_items/batch_size)
    train_data_generator = my_input_fn(total_items, epochs)
    model.fit_generator(generator=train_data_generator, steps_per_epoch=num_batches, epochs=epochs, verbose=1)

EDIT

As implied by giser_yugang in a comment, it is also possible to do it with my_input_fn() as a function returning the dataset instead of the individual batches.

def my_input_fn(total_items, epochs):
    dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
                                             output_types=(tf.float64, tf.int64))

    dataset = dataset.repeat(epochs)
    dataset = dataset.batch(32)
    return dataset

if __name__ == "__main__":
    tf.enable_eager_execution()

    model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
                                 tf.keras.layers.Dense(64, activation=tf.nn.relu),
                                 tf.keras.layers.Dense(12, activation=tf.nn.softmax)])

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

    total_items = 100
    batch_size = 32
    epochs = 10
    num_batches = int(total_items/batch_size)
    dataset = my_input_fn(total_items, epochs)
    model.fit_generator(dataset, epochs=epochs, steps_per_epoch=num_batches)

There does not appear to be any average performance difference between the approaches.

like image 66
berkelem Avatar answered Nov 13 '22 11:11

berkelem
Sign in to Comment

Related questions

Lowess Smoothing of Time Series data python
Django: Direct assignment to the reverse side of a related set is prohibited. Use username.set() instead
matplotlib Circle patch with alpha produces overlap of edge and facecolor
How to warp an image using deformed mesh
Parsing incomplete json array
Compute the last (decimal) digit of x1 ^ (x2 ^ (x3 ^ (... ^ xn))) [duplicate]
How are the contents of the builtins module available in the global namespace without import in Python?
how to print the default value if argument is None in python
Merge on one column or another
Weighted histogram plotly
How are the output size of MaxPooling2D, Conv2D, UpSampling2D layers calculated?
word cloud does not show the frequency of the words correctly
Can't store downloaded files in their concerning folders
after installing uwsgi, python will still error: No module named 'uwsgi'
gRPC server in Python with Unix domain socket
Is it possible to link the interactive python window to a running jupyter notebook kernel?
airflow cleared tasks not getting executed
How to install pip specifically for Python3 on CentOS 7?
Recursively combine dictionaries
jupyterlab doesn't display png image

Donate For Us

If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!