image_dimensions = 3
##########################
# DATA LOADING
##########################
print("Loading paths...")
# download & untar or get local path
base_path = caltech101.download(dataset='img-gen-resized')
# path to image folder
base_path = os.path.join(base_path, caltech101.config.tar_inner_dirname)
# X_test contain only paths to images
(X_test, y_test) = util.load_paths_from_files(base_path, 'X_test.txt',
'y_test.txt')
for cv_fold in [
0
]: # on which cross val folds to run; cant loop over several folds due to some bug
print("fold {}".format(cv_fold))
experiment_name = '_bn_triangular_cv{}_e{}'.format(cv_fold, nb_epoch)
# load cross val split
(X_train, y_train), (X_val,
y_val) = util.load_cv_split_paths(base_path, cv_fold)
# compute class weights, since classes are highly imbalanced
class_weight = compute_class_weight('auto', range(nb_classes), y_train)
def load_train_test_split_paths(base_path):
return load_paths_from_files(base_path, 'X_train.txt', 'y_train.txt'), \
load_paths_from_files(base_path, 'X_test.txt', 'y_test.txt')
image_dimensions = 3
##########################
# DATA LOADING
##########################
print("Loading paths...")
# download & untar or get local path
base_path = caltech101.download(dataset='img-gen-resized')
# path to image folder
base_path = os.path.join(base_path, caltech101.config.tar_inner_dirname)
# X_test contain only paths to images
(X_test, y_test) = util.load_paths_from_files(base_path, 'X_test.txt', 'y_test.txt')
for cv_fold in [0]: # on which cross val folds to run; cant loop over several folds due to some bug
print("fold {}".format(cv_fold))
experiment_name = '_bn_triangular_cv{}_e{}'.format(cv_fold, nb_epoch)
# load cross val split
(X_train, y_train), (X_val, y_val) = util.load_cv_split_paths(base_path, cv_fold)
# compute class weights, since classes are highly imbalanced
class_weight = compute_class_weight('auto', range(nb_classes), y_train)
if normalize_data:
print("Load mean and std...")
X_mean, X_std = util.load_cv_stats(base_path, cv_fold)
import os
from ini_caltech101 import util
path = os.path.abspath(os.path.join('datasets', 'img-gen-resized', '101_ObjectCategories'))
stratify = True
seed = 42
# X_train contain only paths to images
(X_train, y_train) = util.load_paths_from_files(path, 'X_train.txt', 'y_train.txt', full_path=False)
(X_train, y_train) = util.shuffle_data(X_train, y_train, seed=seed)
nb_folds = 10
for cv_fold, ((X_cv_train, y_cv_train), (X_cv_test, y_cv_test)) in \
enumerate(util.make_cv_split(X_train, y_train, nb_folds=nb_folds, stratify=stratify, seed=seed)):
split_config = {'fold': cv_fold,
'nb_folds': nb_folds,
'stratify': stratify,
'seed': seed,
'train_samples': len(X_cv_train),
'test_samples': len(X_cv_test)}
print("Save split for fold {}".format(cv_fold))
util.save_cv_split_paths(path, X_cv_train, y_cv_train, X_cv_test, y_cv_test, cv_fold, split_config)
print("Calculating mean and std...")
X_mean, X_std = util.calc_stats(X_cv_train, base_path=path)
print("Save stats")
def load_train_test_split_paths(base_path):
return load_paths_from_files(base_path, 'X_train.txt', 'y_train.txt'), \
load_paths_from_files(base_path, 'X_test.txt', 'y_test.txt')
