def exception_thrower():
argdict = rec_eval(expr, memo=memo, print_node_on_error=False)
dataset_info = argdict['dataset_info']
learning_algo = argdict['learning_algo']
hp_space = argdict['hp_space']
pipeline = argdict['pipeline']
n_startup_trials = argdict['n_startup_trials']
n_ok_trials = argdict['n_ok_trials']
batchsize = argdict['batchsize']
min_features = argdict['min_features']
max_features = argdict['max_features']
checkpoint_fname = argdict['checkpoint_fname']
batched_lmap_speed_thresh = argdict['batched_lmap_speed_thresh']
ctrl = argdict['ctrl']
tid = ctrl.current_trial['tid']
# -- checkpoint
if isinstance(ctrl.trials, Trials):
if tid > 0 and tid % checkpoint_every == 0:
save_hp(hp_space, ctrl.trials, n_startup_trials,
checkpoint_fname)
# -- retrieve trials from database
if isinstance(ctrl.trials, MongoTrials):
ctrl.trials.refresh()
# -- check and signal stopping to optimizer
current_ok_trials = count_ok_trials(ctrl.trials)
if current_ok_trials >= n_ok_trials:
raise SimpleHpStop(
'number of ok trials reached - '
'stopping process with %d ok trials out of '
'%d trials.' % (current_ok_trials, tid), ctrl.trials)
# -- feature extraction
slm_t0 = time()
fn_imgs = getattr(dataset_info['data_obj'], dataset_info['fn_imgs'])
imgs = fn_imgs()
limgs = lmap_ndarray(imgs)
X = pyll_theano_batched_lmap(
partial(callpipe1, pipeline),
limgs,
batchsize=batchsize,
print_progress_every=10,
speed_thresh=batched_lmap_speed_thresh,
abort_on_rows_larger_than=max_features,
x_dtype='uint8',
)[:]
feat_set = rec_eval(X, print_node_on_error=False)
slm_time = time() - slm_t0
# -- classification
eval_t0 = time()
# -- feat_set in 2-D
feat_shape = feat_set.shape
feat_set.shape = feat_set.shape[0], -1
assert feat_set.shape[1] >= min_features, 'min_features not satisfied'
fn_eval = getattr(dataset_info['data_obj'], dataset_info['fn_eval'])
r_dict = fn_eval(learning_algo, feat_set)
eval_time = time() - eval_t0
r_dict['status'] = hyperopt.STATUS_OK
r_dict['feat_shape'] = feat_shape
r_dict['slm_time'] = slm_time
r_dict['eval_time'] = eval_time
return r_dict
dataset_info = {'data_obj': data_obj,
'fn_imgs': 'hp_imgs',
'fn_eval': 'hp_eval'}
trials = simple_hp(dataset_info, hp_algo, learning_algo, hp_space,
n_startup_trials, n_ok_trials, checkpoint_fname,
host, port)
except SimpleHpStop, e:
msg, trials = e.args
print msg
if opt_mode == 'serial':
# -- save complete hyperparameter optimization trials in pickle format
hp_fname = os.path.join(output_path, 'hp.pkl')
save_hp(hp_space, trials, n_startup_trials, hp_fname)
print 'done!'
def get_optparser():
dataset_options = ''
for k in sorted(datasets.keys()):
dataset_options += (" %s - %s \n" % (k, datasets[k].__name__))
usage = ("usage: %prog <DATASET> <DATASET_PATH>\n\n"
"DATASET is an integer corresponding to the following supported "
"datasets:\n" + dataset_options
)
def exception_thrower():
argdict = rec_eval(expr, memo=memo, print_node_on_error=False)
dataset_info = argdict['dataset_info']
learning_algo = argdict['learning_algo']
hp_space = argdict['hp_space']
pipeline = argdict['pipeline']
n_startup_trials = argdict['n_startup_trials']
n_ok_trials = argdict['n_ok_trials']
batchsize = argdict['batchsize']
min_features = argdict['min_features']
max_features = argdict['max_features']
checkpoint_fname = argdict['checkpoint_fname']
batched_lmap_speed_thresh = argdict['batched_lmap_speed_thresh']
ctrl = argdict['ctrl']
tid = ctrl.current_trial['tid']
# -- checkpoint
if isinstance(ctrl.trials, Trials):
if tid > 0 and tid % checkpoint_every == 0:
save_hp(hp_space, ctrl.trials, n_startup_trials,
checkpoint_fname)
# -- retrieve trials from database
if isinstance(ctrl.trials, MongoTrials):
ctrl.trials.refresh()
# -- check and signal stopping to optimizer
current_ok_trials = count_ok_trials(ctrl.trials)
if current_ok_trials >= n_ok_trials:
raise SimpleHpStop('number of ok trials reached - '
'stopping process with %d ok trials out of '
'%d trials.' % (
current_ok_trials, tid),
ctrl.trials)
# -- feature extraction
slm_t0 = time()
fn_imgs = getattr(dataset_info['data_obj'], dataset_info['fn_imgs'])
imgs = fn_imgs()
limgs = lmap_ndarray(imgs)
X = pyll_theano_batched_lmap(
partial(callpipe1, pipeline),
limgs,
batchsize=batchsize,
print_progress_every=10,
speed_thresh=batched_lmap_speed_thresh,
abort_on_rows_larger_than=max_features,
x_dtype='uint8',
)[:]
feat_set = rec_eval(X, print_node_on_error=False)
slm_time = time() - slm_t0
# -- classification
eval_t0 = time()
# -- feat_set in 2-D
feat_shape = feat_set.shape
feat_set.shape = feat_set.shape[0], -1
assert feat_set.shape[1] >= min_features, 'min_features not satisfied'
fn_eval = getattr(dataset_info['data_obj'], dataset_info['fn_eval'])
r_dict = fn_eval(learning_algo, feat_set)
eval_time = time() - eval_t0
r_dict['status'] = hyperopt.STATUS_OK
r_dict['feat_shape'] = feat_shape
r_dict['slm_time'] = slm_time
r_dict['eval_time'] = eval_time
return r_dict
