def main(archive_dir, hashcode, test_hashcode, num_test, useMpi=False):
if (isinstance(useMpi, str)): useMpi = True if useMpi == "True" else False
print("STARTING: %s" % hashcode)
sys.stdout.flush()
if (useMpi):
p = "../../mpi_learn"
if not p in sys.path:
sys.path.append(p)
from CMS_Deep_Learning.storage.MPIArchiving import MPI_KerasTrial
trial = MPI_KerasTrial.find(archive_dir, hashcode)
else:
trial = KerasTrial.find(archive_dir, hashcode)
print("EXECUTING: %s" % hashcode)
sys.stdout.flush()
trial.execute() #custom_objects={"Lorentz":Lorentz,"Slice": Slice})
rsyncStorable(
trial.hash(), archive_dir,
"[email protected]:/bigdata/shared/Delphes/keras_archive_4_1"
)
#addCommitPushDir(trial.get_path())
return
raise NotImplementedError(
"Will not run test, evaluate_generator acts weird on CSCS")
print("TESTING: %s, num_samples: %r" % (hashcode, num_test))
sys.stdout.flush()
test = DataProcedure.find(archive_dir, test_hashcode)
metrics = trial.test(test_proc=test,
test_samples=num_test,
custom_objects={
"Lorentz": Lorentz,
"Slice": Slice
})
print("DONE: %r" % metrics)
def main(archive_dir, hashcode, test_hashcode, num_test):
print("STARTING: %s" % hashcode)
sys.stdout.flush()
trial = KerasTrial.find_by_hashcode(archive_dir, hashcode)
print("EXECUTING: %s" % hashcode)
sys.stdout.flush()
trial.execute(custom_objects={"Lorentz": Lorentz, "Slice": Slice})
rsyncStorable(
trial.hash(), archive_dir,
"[email protected]:/data/shared/Delphes/CSCS_output/keras_archive"
)
#addCommitPushDir(trial.get_path())
return
raise NotImplementedError(
"Will not run test, evaluate_generator acts weird on CSCS")
print("TESTING: %s, num_samples: %r" % (hashcode, num_test))
sys.stdout.flush()
test = DataProcedure.find_by_hashcode(archive_dir, test_hashcode)
metrics = trial.test(test_proc=test,
test_samples=num_test,
custom_objects={
"Lorentz": Lorentz,
"Slice": Slice
})
print("DONE: %r" % metrics)
def batchExecuteAndTestTrials(tups, time_str="12:00:00", repo="/scratch/daint/dweiteka/CMS_Deep_Learning/", trial_out_dir='/scratch/daint/dweiteka/trial_out/', verbose=1):
'''Takes in a list of tuples 'tups' of the form (trial (a KerasTrial), test (a DataProcedure), num_test (an Integer), deps (a list)), and executes/tests
each trial, either in in order or in separate batches in the case of CSCS.
'''
isdaint = "daint" in socket.gethostname()
scripts_dir = repo + "scripts/"
for trial, test, num_test, deps in tups:
archive_dir = trial.archive_dir
hashcode = trial.hash()
test_hashcode = None
if(test != None):
test.write()
test_hashcode = test.hash()
if(isdaint):
if(not os.path.exists(trial_out_dir)):
os.makedirs(trial_out_dir)
dep_clause = "" if len(deps)==0 else "--dependency=afterok:" + ":".join(deps)
ofile = trial_out_dir + hashcode[:5] + ".%j"
sbatch = 'sbatch -t %s -o %s -e %s %s ' % (time_str,ofile,ofile,dep_clause)
sbatch += '%srunTrial.sh %s %s %s %s %s\n' % (scripts_dir,repo,archive_dir,hashcode, test_hashcode, num_test)
if(verbose >=1): print(sbatch)
out = os.popen(sbatch).read()
if(verbose >=1): print("THIS IS THE OUTPUT:",out)
else:
trial = KerasTrial.find_by_hashcode(archive_dir, hashcode)
if(verbose >=1): print("EXECUTE %r" % trial.hash())
trial.execute(custom_objects={"Lorentz":Lorentz,"Slice": Slice})
if(test_hashcode != None):
if(verbose >=1): print("TEST %r" % trial.hash())
test = DataProcedure.find_by_hashcode(archive_dir,test_hashcode)
trial.test(test_proc=test,
test_samples=num_test,
custom_objects={"Lorentz":Lorentz,"Slice": Slice})
def build_trial(name,
model,
train,
val,
archive_dir=None,
nb_train=None,
nb_val=None,
workers=1,
loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'],
nb_epoch=10,
callbacks=None,
max_q_size=100,
keys_to_record=[],
**kargs):
if isinstance(model, types.FunctionType):
model = model(**kargs)
if (workers == 1):
trial = KerasTrial(archive_dir, name=name, model=model, seed=0)
val, nb_val = assert_dataset(val,
nb_data=nb_val,
as_generator=True,
archive_dir=archive_dir,
**kargs)
train, nb_train = assert_dataset(train,
nb_train,
as_generator=True,
archive_dir=archive_dir,
**kargs)
else:
print("USING MPI")
p = "../../mpi_learn"
if not p in sys.path:
sys.path.append(p)
from CMS_Deep_Learning.storage.MPIArchiving import MPI_KerasTrial
trial = MPI_KerasTrial(archive_dir,
name=name,
model=model,
workers=workers,
seed=0,
features_name="Particles",
labels_name="Labels")
val, nb_val = assert_dataset(val,
nb_data=nb_val,
archive_dir=archive_dir,
**kargs)
train, nb_train = assert_dataset(train,
nb_train,
archive_dir=archive_dir,
**kargs)
trial.set_train(
train_procedure=train, # train_dps,
samples_per_epoch=nb_train)
trial.set_validation(
val_procedure=val, # val_dps,
nb_val_samples=nb_val)
trial.set_compilation(loss=loss, optimizer=optimizer, metrics=metrics)
trial.set_fit_generator(nb_epoch=nb_epoch,
callbacks=callbacks,
max_q_size=max_q_size)
trial.write()
trial.to_record({k: kargs[k] for k in keys_to_record})
return trial