def load_experiments(args):
dataset_name = args.dataset_name
# Load the database and table.
db = sql.db(
"postgres://%(user)s@%(host)s:%(port)d/%(database)s?table=%(table)s" %
{
"user": args.user,
"host": args.host,
"port": args.port,
"database": args.database,
"table": args.table,
})
# Don't worry about this yet.
input_handler = InputHandler()
# For generating models, we use a special set of jobman generators, made
# for convenience.
for items in jg.nested_generator(
jg.float_generator("learning_rate",
3,
0.01,
0.0001,
log_scale=True),
jg.list_generator("nhid", [50, 100, 200, 300]),
):
logger.info("Adding RBM experiment across hyperparameters %s" %
(items, ))
state = DD()
# Load experiment hyperparams from experiment
experiment_hyperparams = experiment.default_hyperparams()
# Set them with values in our loop.
for key, value in items:
split_keys = key.split(".")
entry = experiment_hyperparams
for k in split_keys[:-1]:
entry = entry[k]
assert split_keys[-1] in entry, (
"Key not found in hyperparams: %s" % split_keys[-1])
entry[split_keys[-1]] = value
# Set the dataset name
experiment_hyperparams["dataset_name"] = dataset_name
# Get the input dim and variance map. Don't worry about variance maps right now,
# they aren't used here.
input_dim, variance_map_file = input_handler.get_input_params(
args, experiment_hyperparams)
logger.info("%s\n%s\n" % (input_dim, variance_map_file))
# Set the input dimensionality by the data
experiment_hyperparams["nvis"] = input_dim
# Set the minimum learning rate relative to the initial learning rate.
experiment_hyperparams[
"min_lr"] = experiment_hyperparams["learning_rate"] / 10
# Make a unique hash for experiments. Remember that lists, dicts, and other data
# types may not be hashable, so you may need to do some special processing. In
# this case we convert the lists to tuples.
h = abs(hash(frozenset(flatten(experiment_hyperparams).keys() +\
[tuple(v) if isinstance(v, list)
else v
for v in flatten(experiment_hyperparams).values()])))
# Save path for the experiments. In this case we are sharing a directory in my
# export directory so IT can blame me.
save_path = serial.preprocess(
"/export/mialab/users/dhjelm/pylearn2_outs/rbm_demo/%d" % h)
# We save file params separately as they aren't model specific.
file_params = {
"save_path": save_path,
"variance_map_file": variance_map_file,
}
state.file_parameters = file_params
state.hyper_parameters = experiment_hyperparams
user = path.expandvars("$USER")
state.created_by = user
# Finally we add the experiment to the table.
sql.insert_job(experiment.experiment, flatten(state), db)
# A view can be used when querying the database using psql. May not be needed in future.
db.createView("%s_view" % args.table)
def load_experiments(args):
dataset_name = args.dataset_name
# Load the database and table.
db = sql.db("postgres://%(user)s@%(host)s:%(port)d/%(database)s?table=%(table)s"
% {"user": args.user,
"host": args.host,
"port": args.port,
"database": args.database,
"table": args.table,
})
# Don't worry about this yet.
input_handler = InputHandler()
# For generating models, we use a special set of jobman generators, made
# for convenience.
for items in jg.nested_generator(
jg.float_generator("learning_rate", 3, 0.01, 0.0001, log_scale=True),
jg.list_generator("nhid", [50, 100, 200, 300]),
):
logger.info("Adding RBM experiment across hyperparameters %s" % (items, ))
state = DD()
# Load experiment hyperparams from experiment
experiment_hyperparams = experiment.default_hyperparams()
# Set them with values in our loop.
for key, value in items:
split_keys = key.split(".")
entry = experiment_hyperparams
for k in split_keys[:-1]:
entry = entry[k]
assert split_keys[-1] in entry, ("Key not found in hyperparams: %s"
% split_keys[-1])
entry[split_keys[-1]] = value
# Set the dataset name
experiment_hyperparams["dataset_name"] = dataset_name
# Get the input dim and variance map. Don't worry about variance maps right now,
# they aren't used here.
input_dim, variance_map_file = input_handler.get_input_params(args,
experiment_hyperparams)
logger.info("%s\n%s\n" % (input_dim, variance_map_file))
# Set the input dimensionality by the data
experiment_hyperparams["nvis"] = input_dim
# Set the minimum learning rate relative to the initial learning rate.
experiment_hyperparams["min_lr"] = experiment_hyperparams["learning_rate"] / 10
# Make a unique hash for experiments. Remember that lists, dicts, and other data
# types may not be hashable, so you may need to do some special processing. In
# this case we convert the lists to tuples.
h = abs(hash(frozenset(flatten(experiment_hyperparams).keys() +\
[tuple(v) if isinstance(v, list)
else v
for v in flatten(experiment_hyperparams).values()])))
# Save path for the experiments. In this case we are sharing a directory in my
# export directory so IT can blame me.
save_path = serial.preprocess("/export/mialab/users/dhjelm/pylearn2_outs/rbm_demo/%d"
% h)
# We save file params separately as they aren't model specific.
file_params = {
"save_path": save_path,
"variance_map_file": variance_map_file,
}
state.file_parameters = file_params
state.hyper_parameters = experiment_hyperparams
user = path.expandvars("$USER")
state.created_by = user
# Finally we add the experiment to the table.
sql.insert_job(
experiment.experiment,
flatten(state),
db
)
# A view can be used when querying the database using psql. May not be needed in future.
db.createView("%s_view" % args.table)
