# a dictionary to specify where the dataset path should be
dataset_info = {
"train": {
"img": (".png", "dataset/CoNSeP/Train/Images/"),
"ann": (".mat", "dataset/CoNSeP/Train/Labels/"),
},
"valid": {
"img": (".png", "dataset/CoNSeP/Test/Images/"),
"ann": (".mat", "dataset/CoNSeP/Test/Labels/"),
},
}
patterning = lambda x: re.sub("([\[\]])", "[\\1]", x)
parser = get_dataset(dataset_name)
xtractor = PatchExtractor(win_size, step_size)
for split_name, split_desc in dataset_info.items():
img_ext, img_dir = split_desc["img"]
ann_ext, ann_dir = split_desc["ann"]
out_dir = "%s/%s/%s/%dx%d_%dx%d/" % (
save_root,
dataset_name,
split_name,
win_size[0],
win_size[1],
step_size[0],
step_size[1],
)
file_list = glob.glob(patterning("%s/*%s" % (ann_dir, ann_ext)))
file_list.sort() # ensure same ordering across platform
if cfg.out_preproc is not None:
normalized = (os.path.exists(cfg.out_preproc[mode]) and \
len(os.listdir(cfg.out_preproc[mode])) != 0)
if not normalized:
normalized = False
break
assert (cfg.normalized == normalized)
print(f"Stain normalization was performed: {normalized}")
img_dirs = cfg.out_preproc if normalized else cfg.img_dirs
print(f"Using folders <{list(img_dirs.values())}> as input")
print(f"Saving results to <{list(cfg.out_extract.values())}>")
for data_mode in img_dirs.keys():
xtractor = PatchExtractor(cfg.win_size, cfg.step_size)
img_dir = img_dirs[data_mode]
ann_dir = cfg.labels_dirs[data_mode]
file_list = glob.glob(os.path.join(img_dir, '*{}'.format(cfg.img_ext)))
file_list.sort()
out_dir = cfg.out_extract[data_mode]
rm_n_mkdir(out_dir)
for filename in file_list:
filename = os.path.basename(filename)
basename = filename.split('.')[0]
print('Mode: {}, filename - {}'.format(data_mode, filename))
img = cv2.imread(os.path.join(img_dir, '{}{}'.format(basename, cfg.img_ext)))
import matplotlib.pyplot as plt
import subprocess
#brca = '/data/images/tcga_data/brca/'
#brcaloc = sys.argv[3]
#quip = '/data/images/'
#quiploc = sys.argv[3]
svs = sys.argv[4]
svsloc = sys.argv[3]
outputDir = sys.argv[5]
extract_type = 'mirror'
step_size = [80, 80]
win_size = [540, 540]
xtractor = PatchExtractor(win_size, step_size)
dumppath = sys.argv[1]
segment = int(sys.argv[6])
polygonpath = sys.argv[7] + '{}/*.csv'
manifest = pd.read_csv(os.path.join(dumppath, sys.argv[2]))
manifest["imagepath"] = manifest["imagepath"].str.replace(svs,
svsloc,
regex=False)
remote = int(sys.argv[8])
if remote:
remoteuser = sys.argv[9]
remotekey = sys.argv[10]
def downRemoteFile(path):