Menu
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.
654
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 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.
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.
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.
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.
66
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With