Пример #1
0
def main(tests, root_uri, verbose):
    """Runs RV end-to-end and checks that evaluation metrics are correct."""
    if len(tests) == 0:
        tests = all_tests

    if verbose:
        rv_config.set(verbosity=Verbosity.DEBUG)

    with rv_config.get_tmp_dir() as tmp_dir:
        if root_uri:
            tmp_dir = root_uri

        errors = []
        for test in tests:
            if test not in all_tests:
                print('{} is not a valid test.'.format(test))
                return

            errors.extend(run_test(test, tmp_dir))

            for error in errors:
                print(error)

        for test in tests:
            nb_test_errors = len(
                list(filter(lambda error: error.test == test, errors)))
            if nb_test_errors == 0:
                print('{} test passed!'.format(test))

        if errors:
            exit(1)
Пример #2
0
def run(runner: str, cfg_module: str, commands: List[str],
        arg: List[Tuple[str, str]], splits: int):
    """Run COMMANDS within pipelines in CFG_MODULE using RUNNER.

    RUNNER: name of the Runner to use

    CFG_MODULE: the module with `get_configs` function that returns PipelineConfigs.
    This can either be a Python module path or a local path to a .py file.

    COMMANDS: space separated sequence of commands to run within pipeline. The order in
    which to run them is based on the Pipeline.commands attribute. If this is omitted,
    all commands will be run.
    """
    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    args = dict(arg)
    args = convert_bool_args(args)
    cfgs = get_configs(cfg_module, runner, args)
    runner = registry.get_runner(runner)()

    for cfg in cfgs:
        cfg.update()
        cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
        cfg.recursive_validate_config()

        cfg_dict = cfg.dict()
        cfg_json_uri = cfg.get_config_uri()
        json_to_file(cfg_dict, cfg_json_uri)

        pipeline = cfg.build(tmp_dir)
        if not commands:
            commands = pipeline.commands

        runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
Пример #3
0
def _run_command(cfg_json_uri,
                 command,
                 split_ind=None,
                 num_splits=None,
                 runner=None):
    pipeline_cfg_dict = file_to_json(cfg_json_uri)
    rv_config_dict = pipeline_cfg_dict.get('rv_config')
    rv_config.reset(
        config_overrides=rv_config_dict,
        verbosity=rv_config.verbosity,
        tmp_dir=rv_config.tmp_dir)

    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    cfg = build_config(pipeline_cfg_dict)
    pipeline = cfg.build(tmp_dir)

    if num_splits is not None and split_ind is None and runner is not None:
        runner = registry.get_runner(runner)()
        split_ind = runner.get_split_ind()

    command_fn = getattr(pipeline, command)

    if num_splits is not None and num_splits > 1:
        msg = 'Running {} command split {}/{}...'.format(
            command, split_ind + 1, num_splits)
        click.echo(click.style(msg, fg='green'))
        command_fn(split_ind=split_ind, num_splits=num_splits)
    else:
        msg = 'Running {} command...'.format(command)
        click.echo(click.style(msg, fg='green'))
        command_fn()
Пример #4
0
    def test_accounts_for_aoi(self):
        class_config = ClassConfig(names=['car', 'building', 'background'])

        label_source_uri = data_file_path('evaluator/cc-label-filtered.json')
        label_source_cfg = ChipClassificationLabelSourceConfig(
            vector_source=GeoJSONVectorSourceConfig(uri=label_source_uri,
                                                    default_class_id=None))

        label_store_uri = data_file_path('evaluator/cc-label-full.json')
        label_store_cfg = ChipClassificationGeoJSONStoreConfig(
            uri=label_store_uri)

        raster_source_uri = data_file_path('evaluator/cc-label-img-blank.tif')
        raster_source_cfg = RasterioSourceConfig(uris=[raster_source_uri])

        aoi_uri = data_file_path('evaluator/cc-label-aoi.json')
        s = SceneConfig(id='test',
                        raster_source=raster_source_cfg,
                        label_source=label_source_cfg,
                        label_store=label_store_cfg,
                        aoi_uris=[aoi_uri])

        with rv_config.get_tmp_dir() as tmp_dir:
            scene = s.build(class_config, tmp_dir)
            output_uri = os.path.join(tmp_dir, 'eval.json')

            evaluator = ChipClassificationEvaluatorConfig(
                output_uri=output_uri).build(class_config)
            evaluator.process([scene], tmp_dir)

            overall = file_to_json(output_uri)['overall']
            for item in overall:
                self.assertEqual(item['f1'], 1.0)
Пример #5
0
def run(runner: str, cfg_module: str, commands: List[str],
        arg: List[Tuple[str, str]], splits: int):
    """Subcommand to run commands within pipelines using runner named RUNNER.

    Args:
        runner: name of runner to use
        cfg_module: name of module with `get_configs` function that returns
            PipelineConfigs
        commands: names of commands to run within pipeline. The order in which
            to run them is based on the Pipeline.commands attribute. If this is
            omitted, all commands will be run.
    """
    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    cfg_module = importlib.import_module(cfg_module)
    args = dict(arg)
    args = convert_bool_args(args)
    cfgs = get_configs(cfg_module, runner, args)
    runner = registry.get_runner(runner)()

    for cfg in cfgs:
        cfg.update()
        cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
        cfg.recursive_validate_config()

        cfg_dict = cfg.dict()
        cfg_json_uri = cfg.get_config_uri()
        json_to_file(cfg_dict, cfg_json_uri)

        pipeline = cfg.build(tmp_dir)
        if not commands:
            commands = pipeline.commands

        runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
Пример #6
0
def run(runner, cfg_path, commands, arg, splits):
    """Run commands within pipelines using runner named RUNNER."""
    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    cfg_module = importlib.import_module(cfg_path)
    args = dict(arg)
    args = convert_bool_args(args)
    cfgs = get_configs(cfg_module, runner, args)
    runner = registry.get_runner(runner)()

    for cfg in cfgs:
        cfg.update()
        cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
        cfg.recursive_validate_config()

        cfg_dict = cfg.dict()
        cfg_json_uri = cfg.get_config_uri()
        json_to_file(cfg_dict, cfg_json_uri)

        pipeline = cfg.build(tmp_dir)
        if not commands:
            commands = pipeline.commands

        runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
Пример #7
0
 def setUp(self):
     self.crs_transformer = IdentityCRSTransformer()
     self.extent = Box.make_square(0, 0, 10)
     self.tmp_dir_obj = rv_config.get_tmp_dir()
     self.tmp_dir = self.tmp_dir_obj.name
     self.class_id = 0
     self.background_class_id = 1
     self.line_buffer = 1
     self.class_config = ClassConfig(names=['a'])
     self.uri = join(self.tmp_dir, 'tmp.json')
Пример #8
0
    def setUp(self):
        self.crs_transformer = DoubleCRSTransformer()
        self.geojson = {
            'type':
            'FeatureCollection',
            'features': [{
                'type': 'Feature',
                'geometry': {
                    'type':
                    'MultiPolygon',
                    'coordinates': [[[[0., 0.], [0., 2.], [2., 2.], [2., 0.],
                                      [0., 0.]]]]
                },
                'properties': {
                    'class_name': 'car',
                    'class_id': 0,
                    'score': 0.0
                }
            }, {
                'type': 'Feature',
                'geometry': {
                    'type':
                    'Polygon',
                    'coordinates': [[[2., 2.], [2., 4.], [4., 4.], [4., 2.],
                                     [2., 2.]]]
                },
                'properties': {
                    'score': 0.0,
                    'class_name': 'house',
                    'class_id': 1
                }
            }]
        }

        self.class_config = ClassConfig(names=['car', 'house'])

        self.box1 = Box.make_square(0, 0, 4)
        self.box2 = Box.make_square(4, 4, 4)
        self.class_id1 = 0
        self.class_id2 = 1
        self.background_class_id = 2

        geoms = []
        for f in self.geojson['features']:
            g = shape(f['geometry'])
            g.class_id = f['properties']['class_id']
            geoms.append(g)
        self.str_tree = STRtree(geoms)

        self.file_name = 'labels.json'
        self.tmp_dir = rv_config.get_tmp_dir()
        self.uri = os.path.join(self.tmp_dir.name, self.file_name)
        json_to_file(self.geojson, self.uri)
Пример #9
0
    def setUp(self):
        self.lorem = LOREM

        # Mock S3 bucket
        self.mock_s3 = mock_s3()
        self.mock_s3.start()
        self.s3 = boto3.client('s3')
        self.bucket_name = 'mock_bucket'
        self.s3.create_bucket(Bucket=self.bucket_name)

        # temporary directory
        self.tmp_dir = rv_config.get_tmp_dir()
Пример #10
0
    def setUp(self):
        # Setup mock S3 bucket.
        self.mock_s3 = mock_s3()
        self.mock_s3.start()
        self.s3 = boto3.client('s3')
        self.bucket_name = 'mock_bucket'
        self.s3.create_bucket(Bucket=self.bucket_name)

        self.content_str = 'hello'
        self.file_name = 'hello.txt'
        self.tmp_dir = rv_config.get_tmp_dir()
        self.cache_dir = os.path.join(self.tmp_dir.name, 'cache')
Пример #11
0
def predict(model_bundle, image_uri, output_uri, update_stats, channel_order):
    """Make predictions on the images at IMAGE_URI
    using MODEL_BUNDLE and store the prediction output at OUTPUT_URI.
    """
    if channel_order is not None:
        channel_order = [
            int(channel_ind) for channel_ind in channel_order.split(' ')
        ]

    with rv_config.get_tmp_dir() as tmp_dir:
        predictor = Predictor(model_bundle, tmp_dir, update_stats,
                              channel_order)
        predictor.predict([image_uri], output_uri)
Пример #12
0
    def setUp(self):
        # Setup mock S3 bucket.
        self.mock_s3 = mock_s3()
        self.mock_s3.start()
        self.s3 = boto3.client('s3')
        self.bucket_name = 'mock_bucket'
        self.s3.create_bucket(Bucket=self.bucket_name)

        self.content_str = 'hello'
        self.file_name = 'hello.txt'
        self.s3_path = 's3://{}/{}'.format(self.bucket_name, self.file_name)

        self.tmp_dir = rv_config.get_tmp_dir()
        self.local_path = os.path.join(self.tmp_dir.name, self.file_name)
    def test_stats_transformer(self):
        raster_stats = RasterStats()
        raster_stats.means = list(np.ones((4, )))
        raster_stats.stds = list(np.ones((4, )) * 2)

        with rv_config.get_tmp_dir() as tmp_dir:
            stats_uri = os.path.join(tmp_dir, 'stats.json')
            raster_stats.save(stats_uri)

            # All values have z-score of 1, which translates to
            # uint8 value of 170.
            transformer = StatsTransformerConfig(stats_uri=stats_uri).build()
            chip = np.ones((2, 2, 4)) * 3
            out_chip = transformer.transform(chip)
            expected_out_chip = np.ones((2, 2, 4)) * 170
            np.testing.assert_equal(out_chip, expected_out_chip)
Пример #14
0
def _run_command(cfg_json_uri: str,
                 command: str,
                 split_ind: Optional[int] = None,
                 num_splits: Optional[int] = None,
                 runner: Optional[str] = None):
    """Run a single command using a serialized PipelineConfig.

    Args:
        cfg_json_uri: URI of a JSON file with a serialized PipelineConfig
        command: name of command to run
        split_ind: the index that a split command should assume
        num_splits: the total number of splits to use
        runner: the name of the runner to use
    """
    pipeline_cfg_dict = file_to_json(cfg_json_uri)
    rv_config_dict = pipeline_cfg_dict.get('rv_config')
    rv_config.set_everett_config(profile=rv_config.profile,
                                 config_overrides=rv_config_dict)

    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    cfg = build_config(pipeline_cfg_dict)
    pipeline = cfg.build(tmp_dir)

    if num_splits is not None and split_ind is None and runner is not None:
        runner = registry.get_runner(runner)()
        split_ind = runner.get_split_ind()

    command_fn = getattr(pipeline, command)

    if num_splits is not None and num_splits > 1:
        msg = 'Running {} command split {}/{}...'.format(
            command, split_ind + 1, num_splits)
        click.echo(click.style(msg, fg='green'))
        command_fn(split_ind=split_ind, num_splits=num_splits)
    else:
        msg = 'Running {} command...'.format(command)
        click.echo(click.style(msg, fg='green'))
        command_fn()
Пример #15
0
    def setUp(self):
        self.file_name = 'labels.json'
        self.tmp_dir = rv_config.get_tmp_dir()
        self.file_path = os.path.join(self.tmp_dir.name, self.file_name)

        self.crs_transformer = DoubleCRSTransformer()
        self.geojson = {
            'type':
            'FeatureCollection',
            'features': [{
                'type': 'Feature',
                'geometry': {
                    'type':
                    'Polygon',
                    'coordinates': [[[0., 0.], [0., 1.], [1., 1.], [1., 0.],
                                     [0., 0.]]]
                },
                'properties': {
                    'class_id': 0,
                    'score': 0.9
                }
            }, {
                'type': 'Feature',
                'geometry': {
                    'type':
                    'Polygon',
                    'coordinates': [[[1., 1.], [1., 2.], [2., 2.], [2., 1.],
                                     [1., 1.]]]
                },
                'properties': {
                    'score': 0.9,
                    'class_id': 1
                }
            }]
        }

        self.extent = Box.make_square(0, 0, 10)
        self.class_config = ClassConfig(names=['car', 'house'])
        json_to_file(self.geojson, self.file_path)
Пример #16
0
def run(runner: str, cfg_module: str, commands: List[str],
        arg: List[Tuple[str, str]], splits: int):
    """Run COMMANDS within pipelines in CFG_MODULE using RUNNER.

    RUNNER: name of the Runner to use

    CFG_MODULE: the module with `get_configs` function that returns PipelineConfigs.
    This can either be a Python module path or a local path to a .py file.

    COMMANDS: space separated sequence of commands to run within pipeline. The order in
    which to run them is based on the Pipeline.commands attribute. If this is omitted,
    all commands will be run.
    """
    tmp_dir_obj = rv_config.get_tmp_dir()
    tmp_dir = tmp_dir_obj.name

    args = dict(arg)
    args = convert_bool_args(args)
    cfgs = get_configs(cfg_module, runner, args)
    runner = registry.get_runner(runner)()

    for cfg in cfgs:
        _run_pipeline(cfg, runner, tmp_dir, splits, commands)
Пример #17
0
 def setUp(self):
     self.tmp_dir = rv_config.get_tmp_dir()
     self.uri = os.path.join(self.tmp_dir.name, 'vectors.json')
Пример #18
0
 def setUp(self):
     self.tmp_dir_obj = rv_config.get_tmp_dir()
     self.tmp_dir = self.tmp_dir_obj.name
Пример #19
0
 def setUp(self):
     self.lorem = LOREM
     self.tmp_dir = rv_config.get_tmp_dir()
    def setUp(self):
        self.tmp_dir = rv_config.get_tmp_dir()

        self.class_config = ClassConfig(names=['one', 'two'])
        self.class_config.update()
        self.class_config.ensure_null_class()
Пример #21
0
 def setUp(self):
     self.tmp_dir = rv_config.get_tmp_dir()