def test_meta_provider():
ds_tagged_data = []
for subset in ["train", "val"]:
for category_index in range(10):
for img_index in range(100):
new_object = MockTaggedData(
relative_path=
f"{subset}/cat{category_index}/{img_index}.png",
data=category_index)
ds_tagged_data.append(new_object)
template = "{{subset}}/{{label}}/*.png"
add_label = LabelByTemplate(template=template)
split_into_subset = SplitByTemplate(template=template)
label_to_index = LabelToIndex()
operations = [split_into_subset, add_label, label_to_index]
ds = Dataset(operations=operations, output_function=classification_output)
ds.form(ds_tagged_data)
ds_mapping = ds.meta.index_to_label
for label, value in ds.train:
assert f"cat{value}" == ds_mapping[label]
def test_selective_operation():
ds_tagged_data = []
for subset in ["train", "val"]:
for category_index in range(10):
for img_index in range(100):
new_object = MockTaggedData(
relative_path=f"{subset}/cat{category_index}/{img_index}.png", data=category_index
)
ds_tagged_data.append(new_object)
template = "{{subset}}/{{label}}/*.png"
add_label = LabelByTemplate(template=template)
split_into_subset = SplitByTemplate(template=template)
limit_train = LimitSamplesByBin(sample_limit=50, bin_creator=lambda x: x.label)
limit_val = LimitSamplesByBin(sample_limit=10, bin_creator=lambda x: x.label)
limit_both = SelectiveSubsetOperation({"train": limit_train, "val": limit_val})
operations = [split_into_subset, add_label, limit_both]
ds = Dataset(operations=operations, output_function=classification_output)
ds.form(ds_tagged_data)
assert len(ds.train) == 50 * 10
assert len(ds.val) == 10 * 10
def test_splitting(mask_dataset):
operation_list = [SplitByTemplate("{{ subset }}/*")]
ds = Dataset(operations=operation_list)
ds.form(mask_dataset)
assert len(ds.train) + len(ds.test) + len(ds.val) == len(ds)
assert len(ds) == len(mask_dataset)
def test_dropping(mask_dataset):
operation_list = [DropByTemplate("*/mask*.jpg")]
ds = Dataset(operations=operation_list)
ds.form(mask_dataset)
assert len(ds) * 2 == len(mask_dataset)
for ds_object in ds.objects:
assert "mask" not in ds_object.relative_path
def test_different_input():
ds_tagged_data = [MockTaggedData(f"{i}.png", i) for i in range(10)]
ds = Dataset(output_function=triple_output)
ds.form(ds_tagged_data)
possible_values = {i * 3 for i in range(10)}
for ds_object in ds:
assert ds_object in possible_values
possible_values.remove(ds_object)
def test_splitting_and_combining(mask_dataset):
mask_template = MaskTemplate(image="{{subset}}/image_{{img_id}}.jpg", mask="{{subset}}/mask_{{img_id}}.jpg")
operation_list = [
SplitByTemplate("{{ subset }}/*"),
MaskByTemplate(mask_template),
]
ds1 = Dataset(operations=operation_list)
ds1.form(mask_dataset)
assert (len(ds1.train) + len(ds1.test) + len(ds1.val)) * 2 == len(ds1)
def test_coco(detection_collection):
images, label_mapping = detection_collection
coco_dict = detection_collection_to_coco_dict(images, label_mapping)
annotation_file = MockTaggedData(relative_path="train.json",
data=coco_dict)
tagged_data = [annotation_file
] + [detection_input for detection_input in images]
coco_transform = SingleCoco(annotation_file="train.json", data_folder="")
ds = Dataset(operations=[coco_transform])
ds.form(tagged_data)
assert len(ds) == len(images)
def test_adding():
ds_tagged_data = []
for subset in ["train", "val"]:
for img_index in range(100):
new_object = MockTaggedData(
relative_path=f"{subset}/{img_index}.png",
data=f"{subset}/{img_index}.png")
ds_tagged_data.append(new_object)
template = "{{subset}}/*.png"
split_into_subset = SplitByTemplate(template=template)
operations = [split_into_subset]
ds = Dataset(operations=operations, output_function=classification_output)
ds.form(ds_tagged_data)
assert len(ds) == len(ds.train + ds.val)
assert set(ds.objects) == set((ds.train + ds.val).objects)
def test_combining_mask_img(mask_dataset):
mask_template = MaskTemplate(image="{{subset}}/image_{{img_id}}.jpg", mask="{{subset}}/mask_{{img_id}}.jpg")
operation_list = [MaskByTemplate(mask_template)]
ds = Dataset(operations=operation_list, output_function=single_mask_output)
ds.form(mask_dataset)
assert len(ds.objects) == len(mask_dataset) // 2
for ds_object in ds.objects:
img, mask = ds_object.output()
assert isinstance(img, np.ndarray)
assert isinstance(mask, np.ndarray)
img_path = ds_object.relative_path
mask_path = ds_object.annotations[0].relative_path
assert "image" in img_path
assert "mask" in mask_path
img_data = img_path.replace("image", "")
mask_data = mask_path.replace("mask", "")
assert img_data == mask_data