def load_train_classifier(params, features, labels, feature_names, sizes,
nb_holdout):
logging.info('train classifier...')
seg_clf.feature_scoring_selection(features, labels, feature_names,
path_out=params['path_exp'])
cv = seg_clf.CrossValidatePSetsOut(sizes, nb_hold_out=nb_holdout)
# feature norm & train classification
fname_classif = seg_clf.TEMPLATE_NAME_CLF.format(params['classif'])
path_classif = os.path.join(params['path_exp'], fname_classif)
if os.path.isfile(path_classif) and not FORCE_RETRAIN_CLASSIF:
logging.info('loading classifier: %s', path_classif)
params_local = params.copy()
dict_classif = seg_clf.load_classifier(path_classif)
classif = dict_classif['clf_pipeline']
params = dict_classif['params']
params.update({k: params_local[k] for k in params_local
if k.startswith('path_') or k.startswith('gc_')})
logging.debug('loaded PARAMETERS: %s', repr(params))
else:
classif, path_classif = seg_clf.create_classif_train_export(
params['classif'], features, labels, cross_val=cv,
params=params, feature_names=feature_names,
nb_search_iter=params['nb_classif_search'],
nb_jobs=params['nb_jobs'], pca_coef=params['pca_coef'],
path_out=params['path_exp'])
params['path_classif'] = path_classif
cv = seg_clf.CrossValidatePSetsOut(sizes, nb_hold_out=nb_holdout)
seg_clf.eval_classif_cross_val_scores(params['classif'], classif,
features, labels, cross_val=cv, path_out=params['path_exp'])
seg_clf.eval_classif_cross_val_roc(params['classif'], classif,
features, labels, cross_val=cv, path_out=params['path_exp'])
return params, classif, path_classif
def main_train(params):
""" PIPELINE for training
0) load triplets or create triplets from path to images, annotations
1) load precomputed data or compute them now
2) train classifier with hyper-parameters
3) perform Leave-One-Out experiment
:param {str: any} params:
"""
logging.info('run TRAINING...')
params = prepare_experiment_folder(params, FOLDER_EXPERIMENT)
tl_expt.set_experiment_logger(params['path_expt'])
logging.info(tl_expt.string_dict(params, desc='PARAMETERS'))
with open(os.path.join(params['path_expt'], NAME_JSON_PARAMS), 'w') as f:
json.dump(params, f)
tl_expt.create_subfolders(params['path_expt'], LIST_SUBDIRS)
df_paths, _ = load_df_paths(params)
path_dump_data = os.path.join(params['path_expt'], NAME_DUMP_TRAIN_DATA)
if not os.path.isfile(path_dump_data) or FORCE_RECOMP_DATA:
dict_imgs, dict_segms, dict_slics, dict_points, dict_centers, \
dict_features, dict_labels, feature_names = \
dataset_load_images_segms_compute_features(params, df_paths,
params['nb_jobs'])
assert len(dict_imgs) > 0, 'missing images'
save_dump_data(path_dump_data, dict_imgs, dict_segms, dict_slics,
dict_points, dict_centers, dict_features, dict_labels,
feature_names)
else:
dict_imgs, dict_segms, dict_slics, dict_points, dict_centers, dict_features, \
dict_labels, feature_names = load_dump_data(path_dump_data)
if is_drawing(params['path_expt']) and EXPORT_TRAINING_DATA:
export_dataset_visual(params['path_expt'], dict_imgs, dict_segms,
dict_slics, dict_points, dict_labels,
params['nb_jobs'])
# concentrate features, labels
features, labels, sizes = seg_clf.convert_set_features_labels_2_dataset(
dict_features,
dict_labels,
drop_labels=[-1],
balance_type=params['balance'])
# remove all bad values from features space
features[np.isnan(features)] = 0
features[np.isinf(features)] = -1
assert np.sum(sizes) == len(labels), \
'not equal sizes (%d) and labels (%i)' \
% (int(np.sum(sizes)), len(labels))
# feature norm & train classification
nb_holdout = int(np.ceil(len(sizes) * CROSS_VAL_LEAVE_OUT_SEARCH))
cv = seg_clf.CrossValidatePSetsOut(sizes, nb_holdout)
classif, params['path_classif'] = seg_clf.create_classif_train_export(
params['classif'],
features,
labels,
cross_val=cv,
params=params,
feature_names=feature_names,
nb_search_iter=params['nb_classif_search'],
pca_coef=params.get('pca_coef', None),
nb_jobs=params['nb_jobs'],
path_out=params['path_expt'])
nb_holdout = int(np.ceil(len(sizes) * CROSS_VAL_LEAVE_OUT_EVAL))
cv = seg_clf.CrossValidatePSetsOut(sizes, nb_holdout)
seg_clf.eval_classif_cross_val_scores(params['classif'],
classif,
features,
labels,
cross_val=cv,
path_out=params['path_expt'])
seg_clf.eval_classif_cross_val_roc(params['classif'],
classif,
features,
labels,
cross_val=cv,
path_out=params['path_expt'])
if RUN_LEAVE_ONE_OUT:
experiment_loo(classif, dict_imgs, dict_segms, dict_centers,
dict_slics, dict_points, dict_features, feature_names)
logging.info('DONE')
def train_classif_color2d_slic_features(list_images,
list_annots,
dict_features,
sp_size=30,
sp_regul=0.2,
clf_name=CLASSIF_NAME,
label_purity=0.9,
feature_balance='unique',
pca_coef=None,
nb_classif_search=1,
nb_hold_out=CROSS_VAL_LEAVE_OUT,
nb_jobs=1):
""" train classifier on list of annotated images
:param [ndarray] list_images:
:param [ndarray] list_annots:
:param int sp_size: initial size of a superpixel(meaning edge lenght)
:param float sp_regul: regularisation in range(0;1) where "0" gives elastic
and "1" nearly square segments
:param {str: [str]} dict_features: list of features to be extracted
:param str clf_name: selet udsed classifier
:param float label_purity: set the sample-labels purity for training
:param str feature_balance: set how to balance datasets
:param float pca_coef: select PCA coef or None
:param int nb_classif_search: number of tries for hyper-parameters seach
:param int nb_hold_out: cross-val leave out
:param int nb_jobs: parallelism
:return:
"""
logging.info('TRAIN Superpixels-Features-Classifier')
assert len(list_images) == len(list_annots), \
'size of images (%i) and annotations (%i) should match' \
% (len(list_images), len(list_annots))
list_slic, list_features, list_labels = list(), list(), list()
_wrapper_compute = partial(wrapper_compute_color2d_slic_features_labels,
sp_size=sp_size,
sp_regul=sp_regul,
dict_features=dict_features,
label_purity=label_purity)
list_imgs_annot = zip(list_images, list_annots)
iterate = tl_expt.WrapExecuteSequence(
_wrapper_compute,
list_imgs_annot,
desc='compute SLIC & features & labels',
nb_jobs=nb_jobs)
for slic, fts, lbs in iterate:
list_slic.append(slic)
list_features.append(fts)
list_labels.append(lbs)
logging.debug('concentrate features...')
# concentrate features, labels
features, labels, sizes = seg_clf.convert_set_features_labels_2_dataset(
dict(zip(range(len(list_features)), list_features)),
dict(zip(range(len(list_labels)), list_labels)),
balance_type=feature_balance,
drop_labels=[-1])
# drop do not care label whichare -1
features = np.nan_to_num(features)
logging.debug('train classifier...')
# clf_pipeline = seg_clf.create_clf_pipeline(clf_name, pca_coef)
# clf_pipeline.fit(np.array(features), np.array(labels, dtype=int))
if len(sizes) > (nb_hold_out * 5):
cv = seg_clf.CrossValidatePSetsOut(sizes, nb_hold_out=nb_hold_out)
# for small nuber of training images this does not make sence
else:
cv = 10
classif, _ = seg_clf.create_classif_train_export(
clf_name,
features,
labels,
pca_coef=pca_coef,
cross_val=cv,
nb_search_iter=nb_classif_search,
nb_jobs=nb_jobs)
return classif, list_slic, list_features, list_labels