def test_class_match_segmentation(self):
"""Test class match function for segmentation problems"""
ml_type = 'segmentation'
class_index = 2
passing = np.ones((256, 256), dtype=np.int) * 2
failing = np.ones((256, 256), dtype=np.int)
self.assertTrue(class_match(ml_type, passing, class_index))
self.assertFalse(class_match(ml_type, failing, class_index))
def test_class_match_object(self):
"""Test class match function for object detection problems"""
ml_type = 'object-detection'
class_index = 2
passing = np.array([[0, 0, 0, 0, 2]])
failing = np.array([[0, 0, 0, 0, 1]])
self.assertTrue(class_match(ml_type, passing, class_index))
self.assertFalse(class_match(ml_type, failing, class_index))
def test_class_match_classification(self):
"""Test class match function for classification problems"""
ml_type = 'classification'
class_index = 2
passing = np.array([0, 0, 1])
failing = np.array([0, 1, 0])
self.assertTrue(class_match(ml_type, passing, class_index))
self.assertFalse(class_match(ml_type, failing, class_index))
def _tile_results_summary(ml_type, classes):
print('---')
labels = list(tile_results.values())
all_tiles = list(tile_results.keys())
if ml_type == 'object-detection':
# for each class, show number of features and number of tiles
for i, cl in enumerate(classes):
cl_features = len(
[bb for l in labels for bb in l if bb[4] == i + 1])
cl_tiles = len([
l for l in labels if len(list(filter(_bbox_class(i + 1), l)))
]) # pylint: disable=cell-var-from-loop
print('{}: {} features in {} tiles'.format(cl.get('name'),
cl_features, cl_tiles))
elif ml_type == 'classification':
class_tile_counts = list(np.sum(labels, axis=0))
for i, cl in enumerate(classes):
print('{}: {} tiles'.format(cl.get('name'),
int(class_tile_counts[i + 1])))
elif ml_type == 'segmentation':
for i, cl in enumerate(classes):
count = len([l for l in labels if class_match(ml_type, l, i + 1)])
print('{}: {} tiles'.format(cl.get('name'), count))
print('Total tiles: {}'.format(len(all_tiles)))
def make_labels(dest_folder, zoom, country, classes, ml_type, bounding_box,
sparse, **kwargs):
"""Create label data from OSM QA tiles for specified classes
Perform the following operations:
- If necessary, re-tile OSM QA Tiles to the specified zoom level
- Iterate over all tiles within the bounding box and produce a label for each
- Save the label file as labels.npz
- Create an output for previewing the labels (GeoJSON or PNG depending upon ml_type)
Parameters
------------
dest_folder: str
Folder to save labels and example tiles into
zoom: int
The zoom level to create tiles at
country: str
The OSM QA Tile extract to download. The value should be a country string matching a value found in
`label_maker/countries.txt`
classes: list
A list of classes for machine learning training. Each class is defined as a dict
with two required properties:
- name: class name
- filter: A Mapbox GL Filter.
See the README for more details
ml_type: str
Defines the type of machine learning. One of "classification", "object-detection", or "segmentation"
bounding_box: list
The bounding box to create images from. This should be given in the form: `[xmin, ymin, xmax, ymax]`
as longitude and latitude values between `[-180, 180]` and `[-90, 90]` respectively
sparse: boolean
Limit the total background tiles to write based on `background_ratio` kwarg.
geojson: str
Filepath to optional geojson label input
**kwargs: dict
Other properties from CLI config passed as keywords to other utility functions
"""
mbtiles_file = op.join(dest_folder, '{}.mbtiles'.format(country))
mbtiles_file_zoomed = op.join(dest_folder,
'{}-z{!s}.mbtiles'.format(country, zoom))
if not op.exists(mbtiles_file_zoomed):
filtered_geo = kwargs.get('geojson') or op.join(
dest_folder, '{}.geojson'.format(country))
fast_parse = []
if not op.exists(filtered_geo):
fast_parse = ['-P']
print('Retiling QA Tiles to zoom level {} (takes a bit)'.format(
zoom))
ps = Popen(['tippecanoe-decode', '-c', '-f', mbtiles_file],
stdout=PIPE)
stream_filter_fpath = op.join(op.dirname(label_maker.__file__),
'stream_filter.py')
run([
sys.executable, stream_filter_fpath,
json.dumps(bounding_box)
],
stdin=ps.stdout,
stdout=open(filtered_geo, 'w'))
ps.wait()
run(['tippecanoe', '--no-feature-limit', '--no-tile-size-limit'] +
fast_parse + [
'-l', 'osm', '-f', '-z',
str(zoom), '-Z',
str(zoom), '-o', mbtiles_file_zoomed, filtered_geo
])
# Call tilereduce
print('Determining labels for each tile')
mbtiles_to_reduce = mbtiles_file_zoomed
tilereduce(
dict(zoom=zoom,
source=mbtiles_to_reduce,
bbox=bounding_box,
args=dict(ml_type=ml_type, classes=classes)), _mapper, _callback,
_done)
# Add empty labels to any tiles which didn't have data
empty_label = _create_empty_label(ml_type, classes)
for tile in tiles(*bounding_box, [zoom]):
index = '-'.join([str(i) for i in tile])
global tile_results
if tile_results.get(index) is None:
tile_results[index] = empty_label
# Print a summary of the labels
_tile_results_summary(ml_type, classes)
# If the --sparse flag is provided, limit the total background tiles to write
if sparse:
pos_examples, neg_examples = [], []
for k in tile_results.keys():
# if we don't match any class, this is a negative example
if not sum([
class_match(ml_type, tile_results[k], i + 1)
for i, c in enumerate(classes)
]):
neg_examples.append(k)
else:
pos_examples.append(k)
# Choose random subset of negative examples
n_neg_ex = int(kwargs['background_ratio'] * len(pos_examples))
neg_examples = np.random.choice(neg_examples, n_neg_ex,
replace=False).tolist()
tile_results = {
k: tile_results.get(k)
for k in pos_examples + neg_examples
}
print('Using sparse mode; subselected {} background tiles'.format(
n_neg_ex))
# write out labels as numpy arrays
labels_file = op.join(dest_folder, 'labels.npz')
print('Writing out labels to {}'.format(labels_file))
np.savez(labels_file, **tile_results)
# write out labels as GeoJSON or PNG
if ml_type == 'classification':
features = []
for tile, label in tile_results.items():
feat = feature(Tile(*[int(t) for t in tile.split('-')]))
features.append(
Feature(geometry=feat['geometry'],
properties=dict(label=label.tolist())))
json.dump(fc(features),
open(op.join(dest_folder, 'classification.geojson'), 'w'))
elif ml_type == 'object-detection':
label_folder = op.join(dest_folder, 'labels')
if not op.isdir(label_folder):
makedirs(label_folder)
for tile, label in tile_results.items():
# if we have at least one bounding box label
if bool(label.shape[0]):
label_file = '{}.png'.format(tile)
img = Image.new('RGB', (256, 256))
draw = ImageDraw.Draw(img)
for box in label:
draw.rectangle(((box[0], box[1]), (box[2], box[3])),
outline=class_color(box[4]))
print('Writing {}'.format(label_file))
img.save(op.join(label_folder, label_file))
elif ml_type == 'segmentation':
label_folder = op.join(dest_folder, 'labels')
if not op.isdir(label_folder):
makedirs(label_folder)
for tile, label in tile_results.items():
# if we have any class pixels
if np.sum(label):
label_file = '{}.png'.format(tile)
visible_label = np.array([
class_color(l) for l in np.nditer(label)
]).reshape(256, 256, 3)
img = Image.fromarray(visible_label.astype(np.uint8))
print('Writing {}'.format(label_file))
img.save(op.join(label_folder, label_file))
def preview(dest_folder, number, classes, imagery, ml_type, imagery_offset,
**kwargs):
"""Produce imagery examples for specified classes
Parameters
------------
dest_folder: str
Folder to save labels and example tiles into
number: int
Number of preview images to download per class
classes: list
A list of classes for machine learning training. Each class is defined as a dict
with two required properties:
- name: class name
- filter: A Mapbox GL Filter.
See the README for more details
imagery: str
Imagery template to download satellite images from.
Ex: http://a.tiles.mapbox.com/v4/mapbox.satellite/{z}/{x}/{y}.jpg?access_token=ACCESS_TOKEN
ml_type: str
Defines the type of machine learning. One of "classification", "object-detection", or "segmentation"
imagery_offset: list
An optional list of integers representing the number of pixels to offset imagery. Ex. [15, -5] will
move the images 15 pixels right and 5 pixels up relative to the requested tile bounds
**kwargs: dict
Other properties from CLI config passed as keywords to other utility functions
"""
# open labels file
labels_file = op.join(dest_folder, 'labels.npz')
tiles = np.load(labels_file)
# create example tiles directory
examples_dir = op.join(dest_folder, 'examples')
if not op.isdir(examples_dir):
makedirs(examples_dir)
# find examples tiles for each class and download
print('Writing example images to {}'.format(examples_dir))
# get image acquisition function based on imagery string
image_function = download_tile_tms
if is_tif(imagery):
image_function = get_tile_tif
for i, cl in enumerate(classes):
# create class directory
class_dir = op.join(dest_folder, 'examples', cl.get('name'))
if not op.isdir(class_dir):
makedirs(class_dir)
class_tiles = (t for t in tiles.files
if class_match(ml_type, tiles[t], i + 1))
print('Downloading at most {} tiles for class {}'.format(
number, cl.get('name')))
for n, tile in enumerate(class_tiles):
if n > number:
break
tile_img = image_function(tile, imagery, class_dir, imagery_offset)
if ml_type == 'object-detection':
img = Image.open(tile_img)
draw = ImageDraw.Draw(img)
for box in tiles[tile]:
draw.rectangle(((box[0], box[1]), (box[2], box[3])),
outline='red')
img.save(tile_img)
elif ml_type == 'segmentation':
final = Image.new('RGB', (256, 256))
img = Image.open(tile_img)
mask = Image.fromarray(tiles[tile] * 255)
final.paste(img, mask)
final.save(tile_img)
def preview(dest_folder, number, classes, imagery, ml_type, **kwargs):
"""Produce imagery examples for specified classes
Parameters
------------
dest_folder: str
Folder to save labels and example tiles into
number: int
Number of preview images to download per class
classes: list
A list of classes for machine learning training. Each class is defined as a dict
with two required properties:
- name: class name
- filter: A Mapbox GL Filter.
See the README for more details
imagery: str
Imagery template to download satellite images from.
Ex: http://a.tiles.mapbox.com/v4/mapbox.satellite/{z}/{x}/{y}.jpg?access_token=ACCESS_TOKEN
ml_type: str
Defines the type of machine learning. One of "classification", "object-detection", or "segmentation"
**kwargs: dict
Other properties from CLI config passed as keywords to other utility functions
"""
# open labels file
labels_file = op.join(dest_folder, 'labels.npz')
tiles = np.load(labels_file)
# create example tiles directory
examples_dir = op.join(dest_folder, 'examples')
if not op.isdir(examples_dir):
makedirs(examples_dir)
# find examples tiles for each class and download
print('Writing example images to {}'.format(examples_dir))
o = urlparse(imagery)
_, image_format = op.splitext(o.path)
for i, cl in enumerate(classes):
# create class directory
class_dir = op.join(dest_folder, 'examples', cl.get('name'))
if not op.isdir(class_dir):
makedirs(class_dir)
class_tiles = [t for t in tiles.files if class_match(ml_type, tiles[t], i + 1)]
class_tiles = class_tiles[:number]
print('Downloading {} tiles for class {}'.format(len(class_tiles), cl.get('name')))
for tile in class_tiles:
r = requests.get(url(tile.split('-'), imagery))
tile_img = op.join(dest_folder, 'examples', cl.get('name'),
'{}{}'.format(tile, image_format))
open(tile_img, 'wb').write(r.content)
if ml_type == 'object-detection':
img = Image.open(tile_img)
draw = ImageDraw.Draw(img)
for box in tiles[tile]:
draw.rectangle(((box[0], box[1]), (box[2], box[3])), outline='red')
img.save(tile_img)
elif ml_type == 'segmentation':
final = Image.new('RGB', (256, 256))
img = Image.open(tile_img)
mask = Image.fromarray(tiles[tile] * 255)
final.paste(img, mask)
final.save(tile_img)