def update_db(self):
"""
Update the postgresql database with results.
"""
if self.dbdescr == None:
return
assert self.job_id is not None
db = api0.open_db(self.dbdescr)
j = db.get(self.job_id)
for key, value in self.d["logs"].iteritems():
if key in ["cpu", "mem"]:
j[translate_string("stats.%s" % key, "knex")] = value[key][-1]
else:
for channel, channel_value in value.iteritems():
if len(channel_value) > 0:
j[translate_string("results.%s" % channel, "knex")] =\
channel_value[-1]
for stat in self.d["stats"]:
j[translate_string("stats.%s" % stat, "knex")] =\
self.d["stats"][stat]
status = self.d["stats"]["status"]
if status in ["STARTING", "RUNNING (afaik)"]:
j["jobman.status"] = 1
elif status == "KILLED":
j["jobman.status"] = -1
elif status == "COMPLETED":
j["jobman.status"] = 2
table = self.dbdescr.split("table=", 1)[1]
db.createView("%s" % table)
def tfd(n_trials):
ri = numpy.random.random_integers
state = DD()
with open('mnist_powerup_temp_l2.yaml') as ymtmp:
state.yaml_string = ymtmp.read()
state.powerup_nunits = 240
state.powerup_npieces = 5
state.powerup_nunits2 = 240
state.powerup_npieces2 = 5
state.W_lr_scale = 0.04
state.p_lr_scale = 0.01
state.lr_rate = 0.1
state.init_mom = 0.5
state.final_mom = 0.5
state.decay_factor = 0.5
state.max_col_norm = 1.9365
state.save_path = './'
n_pieces = [2, 3, 4, 5]
n_units = [200, 240, 320, 360, 420, 480]
learning_rates = numpy.logspace(numpy.log10(0.09), numpy.log10(1.2), 60)
learning_rate_scalers = numpy.logspace(numpy.log10(0.1), numpy.log10(1), 50)
decay_factors = numpy.logspace(numpy.log10(0.001), numpy.log10(0.06), 40)
max_col_norms = [1.8365, 1.9365, 2.1365, 2.2365, 2.3486]
ind = 0
TABLE_NAME = "powerup_mnist_finest_large_2l"
db = api0.open_db('postgresql://[email protected]/gulcehrc_db?table=' + TABLE_NAME)
for i in xrange(n_trials):
state.lr_rate = learning_rates[ri(learning_rates.shape[0]) - 1]
state.powerup_nunits = n_units[ri(len(n_units)) - 1]
state.powerup_npieces = n_pieces[ri(len(n_pieces) - 1)]
state.powerup_nunits2 = state.powerup_nunits
state.powerup_npieces2 = state.powerup_npieces
state.W_lr_scale = numpy.random.uniform(low=0.09, high=1.0)
state.p_lr_scale = numpy.random.uniform(low=0.09, high=1.0)
state.init_mom = numpy.random.uniform(low=0.3, high=0.6)
state.final_mom = numpy.random.uniform(low=state.init_mom + 0.1, high=0.9)
state.decay_factor = decay_factors[ri(len(decay_factors)) - 1]
state.max_col_norm = max_col_norms[ri(len(max_col_norms)) - 1]
alphabet = list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUWXYZ0123456789')
state.save_path = './'
state.save_path += ''.join(alphabet[:7]) + '_'
sql.insert_job(experiment, flatten(state), db)
ind += 1
db.createView(TABLE_NAME + '_view')
print "{} jobs submitted".format(ind)
def pento(n_trials):
ri = numpy.random.random_integers
state = DD()
with open('mnist_powerup_temp.yaml') as ymtmp:
state.yaml_string = ymtmp.read()
state.powerup_nunits = 240
state.powerup_npieces = 5
state.W_lr_scale = 0.04
state.p_lr_scale = 0.01
state.lr_rate = 0.1
state.l2_pen = 1e-5
state.l2_pen2 = 0.0000
state.init_mom = 0.5
state.final_mom = 0.5
state.decay_factor = 0.5
state.max_col_norm = 1.9365
state.max_col_norm2 = 1.8365
state.batch_size = 128
state.save_path = './'
n_pieces = [2, 3, 4, 5, 6, 8, 10, 12, 14, 16]
n_units = [200, 240, 280, 320, 360, 420, 480]
batch_sizes = [128, 256, 512]
learning_rates = numpy.logspace(numpy.log10(0.001), numpy.log10(1.0), 30)
learning_rate_scalers = numpy.logspace(numpy.log10(0.01), numpy.log10(1), 30)
l2_pen = numpy.logspace(numpy.log10(1e-6), numpy.log10(8*1e-3), 100)
max_col_norms = [1.7365, 1.8365, 1.9365, 2.1365, 2.2365, 2.4365]
ind = 0
TABLE_NAME = "powerup_mnist_1layer_fixed"
db = api0.open_db('postgresql://[email protected]/gulcehrc_db?table=' + TABLE_NAME)
for i in xrange(n_trials):
state.lr_rate = learning_rates[ri(learning_rates.shape[0]) - 1]
state.powerup_nunits = n_units[ri(len(n_units)) - 1]
state.powerup_npieces = n_pieces[ri(len(n_pieces)) - 1]
state.W_lr_scale = learning_rate_scalers[ri(len(learning_rate_scalers)) - 1]
state.p_lr_scale = learning_rate_scalers[ri(len(learning_rate_scalers)) - 1]
state.batch_size = batch_sizes[ri(len(batch_sizes)) - 1]
state.l2_pen = l2_pen[ri(l2_pen.shape[0]) - 1]
state.init_mom = numpy.random.uniform(low=0.3, high=0.6)
state.final_mom = numpy.random.uniform(low=state.init_mom + 0.1, high=0.9)
state.decay_factor = numpy.random.uniform(low=0.01, high=0.05)
state.max_col_norm = max_col_norms[ri(len(max_col_norms)) - 1]
alphabet = list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUWXYZ0123456789')
numpy.random.shuffle(alphabet)
state.save_path = './'
state.save_path += ''.join(alphabet[:7]) + '_'
sql.insert_job(experiment, flatten(state), db)
ind += 1
db.createView(TABLE_NAME + '_view')
print "{} jobs submitted".format(ind)
def update_db(self):
"""
Update the postgresql database with results.
"""
if self.dbdescr == None:
return
assert self.job_id is not None
db = api0.open_db(self.dbdescr)
j = db.get(self.job_id)
for key, value in self.d["logs"].iteritems():
if key in ["cpu", "mem"]:
j[translate_string("stats.%s" % key, "knex")] = value[key][-1]
else:
for channel, channel_value in value.iteritems():
if len(channel_value) > 0:
j[translate_string("results.%s" % channel, "knex")] =\
channel_value[-1]
for stat in self.d["stats"]:
j[translate_string("stats.%s" % stat, "knex")] =\
self.d["stats"][stat]
status = self.d["stats"]["status"]
if status in ["STARTING", "RUNNING (afaik)"]:
j["jobman.status"] = 1
elif status == "KILLED":
j["jobman.status"] = -1
elif status == "COMPLETED":
j["jobman.status"] = 2
table = self.dbdescr.split("table=",1)[1]
db.createView("%s" % table)
def create_jobman_jobs():
#Database operations
TABLE_NAME = "arcade_post_mlp_cv_binary_8x8_40k"
db = api0.open_db('postgresql://[email protected]/gulcehrc_db?table=' + TABLE_NAME)
ri = numpy.random.random_integers
# Default values
state = DD()
state.dataset = \
"/home/gulcehre/dataset/pentomino/experiment_data/pento64x64_40k_seed_23112222.npy"
state.no_of_folds = 5
state.exid = 0
state.n_hiddens = [100, 200, 300]
state.n_hidden_layers = 3
state.learning_rate = 0.001
state.l1_reg = 1e-5
state.l2_reg = 1e-3
state.n_epochs = 2
state.batch_size = 120
state.save_exp_data = True
self.no_of_patches = 64
state.cost_type = "crossentropy"
state.n_in = 8*8
state.n_out = 1
state.best_valid_error = 0.0
state.best_test_error = 0.0
state.valid_obj_path_error = 0.0
state.test_obj_path_error = 0.0
l1_reg_values = [0., 1e-6, 1e-5, 1e-4]
l2_reg_values = [0., 1e-5, 1e-4]
learning_rates = numpy.logspace(numpy.log10(0.0001), numpy.log10(1), 36)
num_hiddens = numpy.logspace(numpy.log10(256), numpy.log10(2048), 24)
for i in xrange(NO_OF_TRIALS):
state.exid = i
state.n_hidden_layers = ri(4)
n_hiddens = []
for i in xrange(state.n_hidden_layers):
n_hiddens.append(int(num_hiddens[ri(num_hiddens.shape[0]) - 1]))
state.n_hiddens = n_hiddens
state.learning_rate = learning_rates[ri(learning_rates.shape[0]) - 1]
state.l1_reg = l1_reg_values[ri(len(l1_reg_values)) - 1]
state.l2_reg = l2_reg_values[ri(len(l2_reg_values)) - 1]
sql.insert_job(experiment, flatten(state), db)
db.createView(TABLE_NAME + "_view")
def tfd(n_trials):
ri = numpy.random.random_integers
state = DD()
with open("tfd_powerup_temp.yaml") as ymtmp:
state.yaml_string = ymtmp.read()
state.powerup_nunits = 240
state.powerup_npieces = 5
state.W_lr_scale = 0.04
state.p_lr_scale = 0.01
state.lr_rate = 0.1
state.l2_pen = 1e-5
state.l2_pen2 = 0.0000
state.init_mom = 0.5
state.final_mom = 0.5
state.decay_factor = 0.5
state.max_col_norm = 1.9365
state.max_col_norm2 = 1.8365
state.save_path = "./"
n_pieces = [2, 3, 4, 5, 6, 8, 10, 12, 14, 16]
n_units = [200, 240, 280, 320, 420]
learning_rates = numpy.logspace(numpy.log10(0.001), numpy.log10(1.0), 32)
learning_rate_scalers = numpy.logspace(numpy.log10(0.01), numpy.log10(1), 30)
l2_pen = numpy.logspace(numpy.log10(1e-6), numpy.log10(3 * 1e-3), 100)
max_col_norms = [1.8365, 1.9365, 2.1365, 2.2365, 2.3486, 2.4365]
ind = 0
TABLE_NAME = "powerup_tfd_1layer_finer_large2"
db = api0.open_db("postgresql://[email protected]/gulcehrc_db?table=" + TABLE_NAME)
for i in xrange(n_trials):
state.lr_rate = learning_rates[ri(learning_rates.shape[0]) - 1]
state.powerup_nunits = n_units[ri(len(n_units)) - 1]
if state.powerup_nunits >= 320:
state.powerup_npieces = n_pieces[ri(low=0, high=5)]
else:
state.powerup_npieces = n_pieces[ri(low=3, high=(len(n_pieces) - 1))]
state.W_lr_scale = learning_rate_scalers[ri(len(learning_rate_scalers)) - 1]
state.p_lr_scale = learning_rate_scalers[ri(len(learning_rate_scalers)) - 1]
state.l2_pen = l2_pen[ri(l2_pen.shape[0]) - 1]
state.init_mom = numpy.random.uniform(low=0.3, high=0.6)
state.final_mom = numpy.random.uniform(low=state.init_mom + 1.0, high=0.9)
state.decay_factor = numpy.random.uniform(low=0.01, high=0.05)
state.max_col_norm = max_col_norms[ri(len(max_col_norms)) - 1]
alphabet = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUWXYZ0123456789")
state.save_path = "./"
state.save_path += "".join(alphabet[:7]) + "_"
sql.insert_job(experiment, flatten(state), db)
ind += 1
db.createView(TABLE_NAME + "_view")
print "{} jobs submitted".format(ind)
def _open_db(self, table_name):
db = self._dbs.get(table_name, None)
if db is None:
logger.debug("Open database's table %s..." % table_name)
db = self._dbs[table_name] = open_db(
self.get_db_string(table_name))
return db
def _open_db(self, table_name):
db = self._dbs.get(table_name, None)
if db is None:
logger.debug("Open database's table %s..." % table_name)
db = self._dbs[table_name] = open_db(
self.get_db_string(table_name))
return db
def insert_jobexp(exp_args, jobman_args):
"""
Insert jobman experiment jobs in a sql database.
Remarks: We have this in a separate module since we can't refer to the jobexp.run function
from within the jobexp module by it's absolute name (else jobman won't find the experiment when run)
:param exp_args:
:param jobman_args:
:return:
"""
table_name = jobman_args.get("table_name", "experiment")
db = api0.open_db('postgres://*****:*****@127.0.0.1/jobbase?table='+table_name)
for arg in jobman_args:
sql.insert_job(predictive_rl.rlglueexp.jobexp.run, flatten(arg), db)
def load_experiments_jobman(experiment_module, jobargs):
"""
Load jobs from experiment onto postgresql database table.
"""
dbdescr = get_desc(jobargs)
db = api0.open_db(dbdescr)
experiment = imp.load_source("module.name", experiment_module)
for i, items in enumerate(experiment.generator):
hyperparams = experiment.default_hyperparams
state = DD()
set_hyper_parameters(hyperparams, **dict((k, v) for k, v in items))
state.hyperparams = translate(hyperparams, "knex")
state["out&path"] = path.abspath(jobargs["out_path"])
state["experiment&module"] = path.abspath(experiment_module)
state["dbdescr"] = dbdescr
sql.insert_job(run_experiment_jobman, flatten(state), db)
db.createView("%s" % jobargs["table"])
def load_experiments_jobman(experiment_module, jobargs):
"""
Load jobs from experiment onto postgresql database table.
"""
dbdescr = get_desc(jobargs)
db = api0.open_db(dbdescr)
experiment = imp.load_source("module.name", experiment_module)
for i, items in enumerate(experiment.generator):
hyperparams = experiment.default_hyperparams
state = DD()
set_hyper_parameters(hyperparams, **dict((k, v) for k, v in items))
state.hyperparams = translate(hyperparams, "knex")
state["out&path"] = path.abspath(jobargs["out_path"])
state["experiment&module"] = path.abspath(experiment_module)
state["dbdescr"] = dbdescr
sql.insert_job(run_experiment_jobman,
flatten(state),
db)
db.createView("%s" % jobargs["table"])
def main(args):
if not args.experiment:
raise ValueError("Must include experiment source file")
global experiment
logger.info("Loading module %s" % args.experiment)
experiment = imp.load_source("module.name", args.experiment)
db = api0.open_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,
})
alerter = Alerter(prompt=args.table)
alerter.start()
manager = JobManager()
manager.start()
jobs = manager.dict()
updater = Updater(manager, alerter, jobs, db)
analyzer = Analyzer(manager, alerter, jobs, db)
table = Table(jobs, db, args.table, updater, analyzer, alerter,
args.reload)
auto_updater = mp.Process(target=auto_update, args=(table, ))
auto_updater.start()
command_line = CommandLine(alerter, table)
command_line.run()
updater.join()
analyzer.join()
def main(args):
if not args.experiment:
raise ValueError("Must include experiment source file")
global experiment
logger.info("Loading module %s" % args.experiment)
experiment = imp.load_source("module.name", args.experiment)
db = api0.open_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,
})
alerter = Alerter(prompt=args.table)
alerter.start()
manager = JobManager()
manager.start()
jobs = manager.dict()
updater = Updater(manager, alerter, jobs, db)
analyzer = Analyzer(manager, alerter, jobs, db)
table = Table(jobs, db, args.table, updater, analyzer, alerter, args.reload)
auto_updater = mp.Process(target=auto_update,
args=(table,))
auto_updater.start()
command_line = CommandLine(alerter, table)
command_line.run()
updater.join()
analyzer.join()
def open_db(jobargs):
dbdescr = get_desc(jobargs)
db = api0.open_db(dbdescr)
return db
from jobman import api0, sql
from jobman.tools import DD, flatten
# Experiment function
from mlp_jobman import experiment
# Database
TABLE_NAME = 'mlp_dumi'
db = api0.open_db(
'postgres://ift6266h10@gershwin/ift6266h10_sandbox_db?table=' + TABLE_NAME)
# Default values
state = DD()
state.learning_rate = 0.01
state.L1_reg = 0.00
state.L2_reg = 0.0001
state.n_iter = 50
state.batch_size = 20
state.n_hidden = 10
# Hyperparameter exploration
for n_hidden in 20, 30:
state.n_hidden = n_hidden
# Explore L1 regularization w/o L2
state.L2_reg = 0.
for L1_reg in 0., 1e-6, 1e-5, 1e-4:
state.L1_reg = L1_reg
# Insert job
sql.insert_job(experiment, flatten(state), db)
from jobman.tools import DD, flatten
from jobman import api0, sql
import numpy
from pylearn2.scripts.jobman import experiment
rng = numpy.random.RandomState(4312987)
if __name__ == '__main__':
db = api0.open_db('postgres://gershwin.iro.umontreal.ca/desjagui_db/aistats12_mnist_500_1000_diag')
state = DD()
state.yaml_template = """
!obj:pylearn2.scripts.train.Train {
"max_epochs": 250,
"save_freq": 10,
"save_path": "dbm",
# dataset below is now (temporarily) obsolete
"dataset": &data !obj:pylearn2.datasets.mnist.MNIST {
"which_set": 'train',
"shuffle": True,
"one_hot": True,
"binarize": %(binarize)i,
},
"model": &model !obj:DBM.dbm.DBM {
"seed" : 123141,
"n_u": [784, %(nu1)i, %(nu2)i],
"lr": %(lr)f,
"flags": {
'enable_natural': %(enable_natural)i,
from jobman.tools import DD, flatten
from jobman import api0, sql
import numpy
from pylearn2.scripts.jobman import experiment
rng = numpy.random.RandomState(4312987)
if __name__ == '__main__':
db = api0.open_db('postgres://opter.iro.umontreal.ca/desjagui_db/nips2013_modes_rbm_exp1_1')
state = DD()
state.yaml_template = """
!obj:pylearn2.scripts.train.Train {
"dataset": &data !obj:deep_tempering.data.test_modes.OnlineModesNIPSDLUFL {},
"model": &model !obj:deep_tempering.rbm.RBM {
"seed" : %(seed)i,
"init_from" : "",
"batch_size" : &batch_size %(batch_size)i,
"n_v" : 784,
"n_h" : &n_h %(nh1)i,
"neg_sample_steps" : 1,
"flags": {
"ml_vbias": 0,
},
"lr_spec" : {
'type': 'linear',
'start': %(lr_start)f,
'end': %(lr_end)f,
},
"""
IMPORTANT: actually runs on sampled MNIST, contrary to nips2013_mnist_tdbn_exp9_1,
which used thresholding to binarize (due to a discrepancy in Pylearn2).
"""
from jobman.tools import DD, flatten
from jobman import api0, sql
import numpy
from pylearn2.scripts.jobman import experiment
rng = numpy.random.RandomState(4312987)
if __name__ == '__main__':
db = api0.open_db('postgres://opter.iro.umontreal.ca/desjagui_db/icml14_dtneg_mnist_tdbn_exp1_1')
state = DD()
state.yaml_template = """
!obj:pylearn2.train.Train {
"dataset": &data !obj:pylearn2.datasets.mnist.MNIST {
"which_set": 'train',
"center": False,
"one_hot": True,
"binarize": 'sample',
},
"model": &model !obj:deep_tempering.tempered_dbn.TemperedDBN {
"max_updates": 2000000,
"flags": {
'train_on_samples': 0,
'order': 'swap_sample_learn',
from jobman.tools import DD, flatten
from jobman import api0, sql
import numpy
from pylearn2.scripts.jobman import experiment
rng = numpy.random.RandomState(4312987)
if __name__ == '__main__':
db = api0.open_db('postgres://opter.iro.umontreal.ca/desjagui_db/nips2013_modes_tdbn_exp3_2')
state = DD()
state.yaml_template = """
!obj:pylearn2.scripts.train.Train {
"dataset": &data !obj:deep_tempering.data.test_modes.OnlineModesNIPSDLUFL {},
"model": &model !obj:deep_tempering.tempered_dbn.TemperedDBN {
"rbm1": &rbm1 !obj:deep_tempering.rbm.RBM {
"seed" : %(seed1)i,
"batch_size" : &batch_size %(batch_size)i,
"n_v" : 784,
"n_h" : &nh1 %(nh1)i,
"gibbs_vhv": True,
"neg_sample_steps" : 1,
"flags": {
'ml_vbias': 0,
},
"lr_spec" : {
'type': 'linear',
'start': %(lr_start)f,
'end': %(lr_end)f,
state.max_iters = 20000
state.n_hids = 200
state.mem_nel = 200
state.mem_size = 28
np.random.seed(3)
ri = np.random.random_integers
learning_rates = np.logspace(np.log10(lr_min), np.log10(lr_max), 100)
stds = np.random.uniform(std_min, std_max, 100)
#Change the table name everytime you try
TABLE_NAME = "adam_grusoft_model_search_v0"
# You should have an account for jobman
db = api0.open_db('postgresql://[email protected]/gulcehrc_db?table=' + TABLE_NAME)
ind = 0
for i in xrange(n_trials):
state.lr = learning_rates[ri(learning_rates.shape[0]) - 1]
state.std = stds[ri(len(stds)) - 1]
state.batch_size = batches[ri(len(batches)) - 1]
state.renormalization_scale = renormalization_scale[ri(len(renormalization_scale)) - 1]
state.mem_nel = mem_nels[ri(len(mem_nels)) - 1]
state.mem_size = mem_sizes[ri(len(mem_sizes)) - 1]
state.std = stds[ri(stds.shape[0]) - 1]
sql.insert_job(memnet.train_model_adam_gru_soft.search_model_adam_gru_soft, flatten(state), db)
ind += 1
db.createView(TABLE_NAME + "_view")
print "{} jobs submitted".format(ind)
def create_jobman_jobs():
#Database operations
TABLE_NAME = "arcade_multi_prmlp_cv_binary_8x8_40k"
db = api0.open_db(
'postgresql://[email protected]/gulcehrc_db?table=' +
TABLE_NAME)
ri = numpy.random.random_integers
# Default values
state = DD()
state.dataset = \
"/home/gulcehre/dataset/pentomino/experiment_data/pento64x64_40k_seed_23112222.npy"
state.no_of_folds = 5
state.exid = 0
state.n_hiddens = [100, 200, 300]
state.n_hidden_layers = 3
state.learning_rate = 0.001
state.l1_reg = 1e-5
state.l2_reg = 1e-3
state.n_epochs = 2
state.batch_size = 120
state.save_exp_data = True
self.no_of_patches = 64
state.cost_type = "crossentropy"
state.n_in = 8 * 8
state.n_out = 1
state.best_valid_error = 0.0
state.best_test_error = 0.0
state.valid_obj_path_error = 0.0
state.test_obj_path_error = 0.0
l1_reg_values = [0., 1e-6, 1e-5, 1e-4]
l2_reg_values = [0., 1e-5, 1e-4]
learning_rates = numpy.logspace(numpy.log10(0.0001), numpy.log10(1), 36)
num_hiddens = numpy.logspace(numpy.log10(256), numpy.log10(2048), 24)
for i in xrange(NO_OF_TRIALS):
state.exid = i
state.n_hidden_layers = ri(4)
n_hiddens = []
for i in xrange(state.n_hidden_layers):
n_hiddens.append(int(num_hiddens[ri(num_hiddens.shape[0]) - 1]))
state.n_hiddens = n_hiddens
state.learning_rate = learning_rates[ri(learning_rates.shape[0]) - 1]
state.l1_reg = l1_reg_values[ri(len(l1_reg_values)) - 1]
state.l2_reg = l2_reg_values[ri(len(l2_reg_values)) - 1]
sql.insert_job(experiment, flatten(state), db)
db.createView(TABLE_NAME + "_view")
from jobman.tools import DD, flatten
from jobman import api0, sql
import numpy
from pylearn2.scripts.jobman import experiment
rng = numpy.random.RandomState(4312987)
if __name__ == '__main__':
db = api0.open_db(
'postgres://gershwin.iro.umontreal.ca/desjagui_db/aistats12_mnist_nat')
state = DD()
state.yaml_template = """
!obj:pylearn2.scripts.train.Train {
"max_epochs": 250,
"save_freq": 10,
"save_path": "dbm",
# dataset below is now (temporarily) obsolete
"dataset": &data !obj:pylearn2.datasets.mnist.MNIST {
"which_set": 'train',
"shuffle": True,
"one_hot": True,
"binarize": %(binarize)i,
},
"model": &model !obj:DBM.dbm.DBM {
"seed" : 123141,
"n_u": [784, %(nu1)i, %(nu2)i],
"lr": %(lr)f,
"flags": {
print "Hello World"
from jobman import api0, sql
from jobman.tools import DD, flatten
print "jobman loaded"
# Experiment function
from test_exp import experiment
print "open database"
# Database
TABLE_NAME = 'mlp_dumi'
db = api0.open_db('postgres://ift6266h13@gershwin/ift6266h13_sandbox_db?table='+TABLE_NAME)
print "database loaded"
# Default values
state = DD()
state.learning_rate = 0.01
state.L1_reg = 0.00
state.L2_reg = 0.0001
state.n_iter = 50
state.batch_size = 20
state.n_hidden = 10
# Hyperparameter exploration
for n_hidden in 20, 30:
print "h_hidden =",h_hidden
from jobman import api0
TABLE_NAME = 'test_add_'
db = api0.open_db('postgres://<user>:<pass>@<server>/<database>?table=' +
TABLE_NAME)
db.createView(TABLE_NAME + 'view')
def open_db(jobargs):
dbdescr = get_desc(jobargs)
db = api0.open_db(dbdescr)
return db
"""
import numpy
channels = train_obj.model.monitor.channels
train_cost = channels['sgd_cost(ExhaustiveSGD[X])']
best_epoch = numpy.argmin(train_cost.val_record)
best_rec_error = train_cost.val_record[best_epoch]
batch_num = train_cost.batch_record[best_epoch]
return dict(
best_epoch=best_epoch,
train_rec_error=best_rec_error,
batch_num=batch_num)
if __name__ == '__main__':
db = api0.open_db('sqlite:///test.db?table=test_jobman_pylearn2')
state = DD()
state.yaml_template = '''
!obj:pylearn2.train.Train {
"dataset": !obj:pylearn2.datasets.npy_npz.NpyDataset &dataset {
"file" : "%(file)s"
},
"model": !obj:pylearn2.autoencoder.ContractiveAutoencoder {
"nvis" : %(nvis)d,
"nhid" : %(nhid)d,
"irange" : 0.05,
"act_enc": "sigmoid", #for some reason only sigmoid function works
"act_dec": "sigmoid",
},
from jobman.tools import DD, flatten
from jobman import api0, sql
from jobman.examples.def_addition import addition_example
TABLE_NAME = 'test_add_'
# DB path...
db = api0.open_db(
'postgres://<user>:<pass>@<server>/<database>?table=' + TABLE_NAME)
state = DD()
for first in 0, 2, 4, 6, 8, 10:
state.first = first
for second in 1, 3, 5, 7, 9:
state.second = second
sql.insert_job(addition_example, flatten(state), db)
