Learning to Learn in TensorFlow
Available items
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
python train.py --problem=mnist --save_path=./mnist
Command-line flags:
save_path: If present, the optimizer will be saved to the specified path every time the evaluation performance is improved.
num_epochs: Number of training epochs.
log_period: Epochs before mean performance and time is reported.
evaluation_period: Epochs before the optimizer is evaluated.
evaluation_epochs: Number of evaluation epochs.
problem: Problem to train on. See Problems section below.
num_steps: Number of optimization steps.
unroll_length: Number of unroll steps for the optimizer.
learning_rate: Learning rate.
second_derivatives: If
true, the optimizer will try to compute second derivatives through the loss function specified by the problem.
python evaluate.py --problem=mnist --optimizer=L2L --path=./mnist
Command-line flags:
optimizer:
Adamor
L2L.
path: Path to saved optimizer, only relevant if using the
L2Loptimizer.
learning_rate: Learning rate, only relevant if using
Adamoptimizer.
num_epochs: Number of evaluation epochs.
seed: Seed for random number generation.
problem: Problem to evaluate on. See Problems section below.
num_steps: Number of optimization steps.
The training and evaluation scripts support the following problems (see
util.pyfor more details):
simple: One-variable quadratic function.
simple-multi: Two-variable quadratic function, where one of the variables is optimized using a learned optimizer and the other one using Adam.
quadratic: Batched ten-variable quadratic function.
mnist: Mnist classification using a two-layer fully connected network.
cifar: Cifar10 classification using a convolutional neural network.
cifar-multi: Cifar10 classification using a convolutional neural network, where two independent learned optimizers are used. One to optimize parameters from convolutional layers and the other one for parameters from fully connected layers.
New problems can be implemented very easily. You can see in
train.pythat the
meta_minimizemethod from the
MetaOptimizerclass is given a function that returns the TensorFlow operation that generates the loss function we want to minimize (see
problems.pyfor an example).
It's important that all operations with Python side effects (e.g. queue creation) must be done outside of the function passed to
meta_minimize. The
cifar10function in
problems.pyis a good example of a loss function that uses TensorFlow queues.
Disclaimer: This is not an official Google product.