def __init__(self,
class_type,
image_dir,
label_filepath,
split,
label2id=None,
randomize=False):
self.class_type = class_type
self.label2id = label2id
self.__labels_csv = csv_utils.read(label_filepath)
self.__metadata_train, self.__metadata_dev, self.__metadata_test = \
self.__read_folders(image_dir, split, randomize)
self.train = CustomDataset(self.__metadata_train, self.label2id,
self.__labels_csv)
self.dev = CustomDataset(self.__metadata_dev, self.label2id,
self.__labels_csv)
self.test = CustomDataset(self.__metadata_test, self.label2id,
self.__labels_csv)
print(len(self.train))
print(len(self.__metadata_train))
print(len(self.dev))
print(len(self.__metadata_dev))
print(len(self.test))
print(len(self.__metadata_test))
assert len(self.train) + len(self.dev) + len(self.test) == \
len(self.__metadata_train) + len(self.__metadata_dev) + len(self.__metadata_test)
def gen_label(self, path, pos_label="mitosis", neg_label="no-mitosis"):
# assuming path = <root>/<img_id>/<img_name>.png
# ex path = root/01/0-101.png
# path = <root>/tiles/12/04/0-600-90.png
img_id = os.path.dirname(path).replace(self.tiles_dir + '/', '')
# img_id = 12/04
try:
x, y, r = os.path.basename(os.path.splitext(path)[0]).split('-')
except:
print(path)
# x = 0, y = 600, r = 90
lbl_path = os.path.join(self.label_dir, img_id + ".csv")
# lbl_path = <root>/labels/12/04.csv
true_labels = []
if os.path.isfile(lbl_path):
true_labels = csv_utils.read(lbl_path, is_headers=False)
# TODO verify row columns for label file
labels = [(int(row[0]), int(row[1])) for row in true_labels]
# labels = [(70, 1782)]
for label in labels:
if (int(x) < int(label[0]) <= int(x) + self.tile_size) and \
(int(y) < int(label[1]) <= int(y) + self.tile_size):
return pos_label
return neg_label
def __init__(self, train_dir, test_dir, train_save_dir, test_save_dir, label_2_id, mu, std, tile_size=299, stride=150,
dev_per=20, order=None, randomize=True, transform=None, redo_preprocessing=False):
self.dir_status_file = ".dir_status"
self.tile_size = tile_size
self.stride = stride
self.randomize = randomize
self.train_dir = train_dir
self.test_dir = test_dir
if transform == 'normalize':
self.transform = self.__normalize
self.mu = mu
self.std = std
# dict [benign:0, normal:1 ...]
self.label_2_id = label_2_id
# get labels ids from csv file
self.train_lbls = csv_utils.read(os.path.join(train_dir, "labels.csv"))
self.test_lbls = csv_utils.read(os.path.join(test_dir, "labels.csv"))
self.dispatch = {
'tile': self.__tile,
'normal_stain': self.__normal_stain,
}
if order is None:
order = ['normal_stain', 'tile']
self.__preprocess_images(train_dir, train_save_dir, order, redo_preprocessing)
self.__preprocess_images(test_dir, test_save_dir, order, redo_preprocessing)
self.__create_dataset(train_save_dir, test_save_dir, dev_per)
def get_label(self, path, x, y):
# assuming path = <root>/<img_id>/<img_name>.png
# path = <root>/tiles/12/04/0-600-90.png
img_id = os.path.splitext(path)[0].replace(self.srcdir + '/', '')
# img_id = 12/04
# x = 0, y = 600, r = 90
lbl_path = os.path.join(self.label_dir, img_id + ".csv")
# lbl_path = <root>/labels/12/04.csv
true_labels = []
if os.path.isfile(lbl_path):
true_labels = csv_utils.read(lbl_path, is_headers=False)
# TODO verify row columns for label file
labels = [(int(row[0]), int(row[1])) for row in true_labels]
# labels = [(70, 1782)]
for label in labels:
if (int(x) < int(label[0]) <= int(x) + self.tile_size) and \
(int(y) < int(label[1]) <= int(y) + self.tile_size):
return self.pos_label
return self.neg_label
def __init__(self,
class_type,
image_dir,
label_filepath,
split,
label2id=None,
transform=None,
filter_model=None,
filter_percent=100):
self.class_type = class_type
self.__labels_csv = csv_utils.read(label_filepath)
if label2id:
self.label2id = label2id
print(self.label2id)
else:
unique = list(OrderedSet(self.__all_labels(self.class_type)))
self.label2id = dict(zip(unique, range(len(unique))))
print(self.label2id)
self.no_labels = len(self.label2id.keys())
self.train, self.dev, self.test = self.gen_triples(image_dir, split, transform, filter_model, filter_percent)