def func_tiny_od_data_path(tmp_session) -> str:
""" Returns the path to the fridge object detection dataset. """
return unzip_url(
od_urls.fridge_objects_tiny_path,
fpath=f"{tmp_session}/tmp",
dest=f"{tmp_session}/tmp",
exist_ok=True,
)
def tiny_ic_data_path(tmp_session) -> str:
""" Returns the path to the tiny fridge objects dataset. """
return unzip_url(
ic_urls.fridge_objects_tiny_path,
fpath=tmp_session,
dest=tmp_session,
exist_ok=True,
)
def tiny_od_mask_data_path(tmp_session) -> str:
""" Returns the path to the fridge object detection mask dataset. """
return unzip_url(
od_urls.fridge_objects_mask_tiny_path,
fpath=tmp_session,
dest=tmp_session,
exist_ok=True,
)
def tiny_od_keypoint_data_path(tmp_session) -> str:
""" Returns the path to the fridge object detection keypoint dataset. """
return unzip_url(
od_urls.fridge_objects_keypoint_milk_bottle_tiny_path,
fpath=tmp_session,
dest=tmp_session,
exist_ok=True,
)
def tiny_ic_databunch(tmp_session):
""" Returns a databunch object for the tiny fridge objects dataset. """
im_paths = unzip_url(Urls.fridge_objects_tiny_path,
tmp_session,
exist_ok=True)
return (ImageList.from_folder(im_paths).split_by_rand_pct(
valid_pct=0.1, seed=20).label_from_folder().transform(
size=50).databunch(bs=16).normalize(imagenet_stats))
def testing_im_list(tmp_session):
""" Set of 5 images from the can/ folder of the Fridge Objects dataset
used to test positive example rank calculations"""
im_paths = unzip_url(Urls.fridge_objects_tiny_path,
tmp_session,
exist_ok=True)
can_im_paths = os.listdir(os.path.join(im_paths, "can"))
can_im_paths = [
os.path.join(im_paths, "can", im_name) for im_name in can_im_paths
][0:5]
return can_im_paths
def test_unzip_url_exist_ok(tmp_path):
"""
Test if exist_ok is true and (file exists, file does not exist)
"""
os.makedirs(tmp_path / "fridgeObjects")
fridge_object_path = unzip_url(Urls.fridge_objects_path,
fpath=tmp_path,
dest=tmp_path,
exist_ok=True)
# should skip unzipping since the path already exist
assert len(os.listdir(fridge_object_path)) == 0
shutil.rmtree(tmp_path / "fridgeObjects")
fridge_object_path = unzip_url(
Urls.fridge_objects_watermark_path,
fpath=tmp_path,
dest=tmp_path,
exist_ok=True,
)
# should unzip all four data class directories
assert len(os.listdir(fridge_object_path)) == 4
def _test_url_data(url: str, path: Union[Path, str], dir_name: str):
dest_path = os.path.join(path, dir_name)
# dir should not exist yet for valid testing
assert not os.path.isdir(dest_path)
unzipped_path = unzip_url(url, fpath=path, dest=path, exist_ok=True)
# assert zip file exists
assert os.path.exists(os.path.join(path, f"{dir_name}.zip"))
# assert unzipped file (titled {dir_name}) exists
assert os.path.exists(dest_path)
# assert unzipped file equals the returned {data_path}
assert os.path.realpath(dest_path) == os.path.realpath(unzipped_path)
def tiny_seg_data_path(tmp_session, seg_classes) -> str:
""" Returns the path to the segmentation tiny fridge objects dataset. """
path = unzip_url(
seg_urls.fridge_objects_tiny_path,
fpath=tmp_session,
dest=tmp_session,
exist_ok=True,
)
classes_path = Path(path) / "classes.txt"
with open(classes_path, "w") as f:
for c in seg_classes:
f.write(c + "\n")
return path
def test_unzip_url_not_exist_ok(tmp_path):
"""
Test if exist_ok is false and (file exists, file does not exist)
"""
os.makedirs(tmp_path / "fridgeObjects")
# should throw an error
with pytest.raises(FileExistsError):
unzip_url(
Urls.fridge_objects_path,
fpath=tmp_path,
dest=tmp_path,
exist_ok=False,
)
shutil.rmtree(tmp_path / "fridgeObjects")
os.remove(tmp_path / "fridgeObjects.zip")
fridge_object_path = unzip_url(Urls.fridge_objects_path,
fpath=tmp_path,
dest=tmp_path,
exist_ok=False)
# should unzip all four data class directories
assert len(os.listdir(fridge_object_path)) == 4
def testing_databunch(tmp_session):
""" Builds a databunch from the Fridge Objects
and returns its validation component that is used
to test comparative_set_builder"""
im_paths = unzip_url(Urls.fridge_objects_tiny_path,
tmp_session,
exist_ok=True)
can_im_paths = os.listdir(os.path.join(im_paths, "can"))
can_im_paths = [
os.path.join(im_paths, "can", im_name) for im_name in can_im_paths
][0:5]
random.seed(642)
data = (ImageList.from_folder(im_paths).split_by_rand_pct(
valid_pct=0.2, seed=20).label_from_folder().transform(
size=300).databunch(bs=16).normalize(imagenet_stats))
validation_bunch = data.valid_ds
return validation_bunch
def multilabel_ic_data_path(tmp_session) -> str:
""" Returns the path to the tiny fridge objects dataset. """
return unzip_url(Urls.multilabel_fridge_objects_path,
tmp_session,
exist_ok=True)
