def gen_cls_dsmd_file_from_datafolder(
root_dir, c2l_path, dsmd_path, classnames=None):
""" Generate classification dataset metadata file from DataFolder for
specified classes.
DataFolder is a directory structure for image classification problems.
Each sub-directory contains images from a special class. DataFolder
directory structure looks like
-----------------------
├── class1
│ ├── 1.png
│ └── 2.png
│ ...
├── class2
│ ├── 3.png
│ └── 4.png
└── ...
-----------------------
Args:
root_dir (str): root data directory containing all the images.
c2l_path (str): file path to save class2label info.
dsmd_path (str): file path to save dataset metadata file.
classnames (list[str]): names of specified classes.
If not given, all classes are considered.
Note:
This function is expected to be used together with
'gen_cls_ds_from_datafolder()'.
Filename of each image in DataFolder should be unique. Otherwise,
A FileExistsError will be thrown.
"""
assert mv.isdir(root_dir)
if classnames is None:
classnames = mv.listdir(root_dir)
class2label = {}
dsmd = {}
for label, classname in enumerate(classnames):
class2label[classname] = label
class_dir = mv.joinpath(root_dir, classname)
assert mv.isdir(class_dir)
filenames = mv.listdir(class_dir)
for filename in filenames:
if filename in dsmd:
raise FileExistsError(
'filename {} already exists'.format(filename))
dsmd[filename] = label
mv.save_dsmd(c2l_path, class2label)
mv.save_dsmd(dsmd_path, dsmd)
def test_mkdirs():
with not_raises(FileExistsError):
mv.mkdirs(DATA_DIR)
path = mv.joinpath(DATA_DIR, 'temporary_subdir')
mv.mkdirs(path)
assert mv.isdir(path)
mv.rmtree(path)
def experiment_exists(experiment):
if not mv.isdir('runs'):
return False
all_experiments = mv.listdir('runs')
all_experiments = [e.split('_', 3)[-1] for e in all_experiments]
if experiment in all_experiments:
return True
else:
return False
def gen_cls_ds_from_datafolder(
in_dir, out_dir, auto_mkdirs=True, classnames=None):
""" Generate classification dataset from DataFolder.
This function will make a copy of each image in the DataFolder to the
specified directory. Original DataFolder is left unchanged.
Args:
in_dir (str): DataFolder root directory.
out_dir (str): directory to save all the images in DataFolder.
auto_mkdirs (bool): If `out_dir` does not exist, whether to create
it automatically.
classnames (list[str]): names of specified classes to be collected.
If not given, all classes are considered.
Note:
This function is expected to be used together with
gen_cls_dsmd_file_from_datafolder().
Filename of each image in DataFolder should be unique. Otherwise,
A FileExistsError will be thrown.
DataFolder is described in 'gen_cls_dsmd_file_from_datafolder()'.
"""
assert mv.isdir(in_dir)
# clean output directory
if auto_mkdirs:
mv.mkdirs(mv.parentdir(out_dir))
mv.empty_dir(out_dir)
if classnames is None:
classnames = mv.listdir(in_dir)
for classname in classnames:
class_dir = mv.joinpath(in_dir, classname)
assert mv.isdir(class_dir)
filenames = natsorted(mv.listdir(class_dir))
mv.copyfiles(filenames, out_dir, class_dir, non_overwrite=True)
def test_copyfiles():
dst_dir = mv.joinpath(DATA_DIR, 'temporary_subdir')
mv.mkdirs(dst_dir)
src_paths = ['brain_001.dcm', 'brain_002.dcm']
mv.copyfiles(src_paths, dst_dir, DCM_DIR)
assert len(mv.listdir(dst_dir)) == 2
with not_raises(FileExistsError):
mv.copyfiles(src_paths, dst_dir, DCM_DIR, non_overwrite=False)
with pytest.raises(FileExistsError):
mv.copyfiles(src_paths, dst_dir, DCM_DIR, non_overwrite=True)
mv.empty_dir(dst_dir)
assert mv.isdir(dst_dir)
assert len(mv.listdir(dst_dir)) == 0
mv.rmtree(dst_dir)
def isdicomdir(path):
""" Judge whether a given directory is a valid dicom directory.
If given directory only contains dicoms (at least one dicom file),
it is a dicom directory. Otherwise, it is not a dicom directory.
Args:
path(str): given directory path.
Returns:
(bool): True if given directory path is a dicom directory,
otherwise False.
"""
if not mv.isdir(path):
return False
for file_name in mv.listdir(path):
file_path = mv.joinpath(path, file_name)
if not isdicom(file_path):
return False
else:
return True
def __init__(self, cfg, mode, build_transform, image_loader):
self.is_train = (mode == mv.ModeKey.TRAIN)
self.mode2dsmd = {
mv.ModeKey.TRAIN: cfg.DATA.TRAIN_DSMD,
mv.ModeKey.VAL: cfg.DATA.VAL_DSMD,
mv.ModeKey.TEST: cfg.DATA.TEST_DSMD,
}
dsmd_path = self.mode2dsmd[mode]
assert mv.isfile(dsmd_path) or mv.isdir(dsmd_path)
if mv.isfile(dsmd_path): # for a dsmd file
self.dsmd = mv.load_dsmd(dsmd_path)
self.filenames = list(self.dsmd.keys())
self.filepaths = [
mv.joinpath(cfg.DATA.IMAGE_DIR, filename)
for filename in self.filenames
]
else: # for a directory containing test images
self.dsmd = None
self.filepaths = mv.listdir(dsmd_path)
self.transform = build_transform(cfg, self.is_train)
self.image_loader = image_loader
