def test_2nn_output_shape(self):
image = tf.random.normal([7, 28, 28, 1])
model = emnist_models.create_two_hidden_layer_model(only_digits=False,
hidden_units=200)
logits = model(image)
self.assertIsNotNone(logits)
self.assertEqual(logits.shape, [7, 62])
def test_2nn_number_of_parameters(self):
model = emnist_models.create_two_hidden_layer_model(only_digits=True,
hidden_units=200)
# We calculate the number of parameters based on the fact that given densely
# connected layers of size n and m with bias units, there are (n+1)m
# parameters between these layers. The network above should have layers of
# size 28*28, 200, 200, and 10.
num_model_params = (28 * 28 + 1) * 200 + 201 * 200 + 201 * 10
self.assertEqual(model.count_params(), num_model_params)
def run_centralized(optimizer: tf.keras.optimizers.Optimizer,
experiment_name: str,
root_output_dir: str,
num_epochs: int,
batch_size: int,
decay_epochs: Optional[int] = None,
lr_decay: Optional[float] = None,
hparams_dict: Optional[Mapping[str, Any]] = None,
emnist_model: Optional[str] = 'cnn',
max_batches: Optional[int] = None):
"""Trains a model on EMNIST character recognition using a given optimizer.
Args:
optimizer: A `tf.keras.optimizers.Optimizer` used to perform training.
experiment_name: The name of the experiment. Part of the output directory.
root_output_dir: The top-level output directory for experiment runs. The
`experiment_name` argument will be appended, and the directory will
contain tensorboard logs, metrics written as CSVs, and a CSV of
hyperparameter choices (if `hparams_dict` is used).
num_epochs: The number of training epochs.
batch_size: The batch size, used for train, validation, and test.
decay_epochs: The number of epochs of training before decaying the learning
rate. If None, no decay occurs.
lr_decay: The amount to decay the learning rate by after `decay_epochs`
training epochs have occurred.
hparams_dict: A mapping with string keys representing the hyperparameters
and their values. If not None, this is written to CSV.
emnist_model: A string specifying the model used for character recognition.
Can be one of `cnn` and `2nn`, corresponding to a CNN model and a densely
connected 2-layer model (respectively).
max_batches: If set to a positive integer, datasets are capped to at most
that many batches. If set to None or a nonpositive integer, the full
datasets are used.
"""
train_dataset, eval_dataset = emnist_dataset.get_centralized_datasets(
train_batch_size=batch_size,
max_train_batches=max_batches,
max_test_batches=max_batches,
only_digits=False)
if emnist_model == 'cnn':
model = emnist_models.create_conv_dropout_model(only_digits=False)
elif emnist_model == '2nn':
model = emnist_models.create_two_hidden_layer_model(only_digits=False)
else:
raise ValueError(
'Cannot handle model flag [{!s}].'.format(emnist_model))
model.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(),
optimizer=optimizer,
metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
centralized_training_loop.run(keras_model=model,
train_dataset=train_dataset,
validation_dataset=eval_dataset,
experiment_name=experiment_name,
root_output_dir=root_output_dir,
num_epochs=num_epochs,
hparams_dict=hparams_dict,
decay_epochs=decay_epochs,
lr_decay=lr_decay)