def main(args, _=None): args = args.__dict__ args.pop("command", None) num_workers = args.pop("num_workers") with get_pool(num_workers) as p: Preprocessor(**args).process_all(p)
def main() -> None: """Run ``esrgan-process-images`` script.""" args = args = parse_args().__dict__ num_workers = args.pop("num_workers") with utils.get_pool(num_workers) as p: Preprocessor(**args).process_all(p)
def main(args, _=None): """Run the ``catalyst-data process-images`` script.""" args = args.__dict__ args.pop("command", None) num_workers = args.pop("num_workers") with get_pool(num_workers) as p: Preprocessor(**args).process_all(p)
def main(args, _=None): with get_pool(args.num_workers) as pool: images = os.listdir(args.in_dir) colors = tqdm_parallel_imap(colors_in_image, images, pool) unique_colors = reduce(lambda s1, s2: s1 | s2, colors) index2color = collections.OrderedDict([ (index, color) for index, color in enumerate(sorted(unique_colors)) ]) print("Num classes: ", len(index2color)) with open(args.out_labeling, "w") as fout: json.dump(index2color, fout, indent=4)
def main(args): df = pd.read_csv(args.in_csv) if args.datapath: df["datapath"] = args.datapath if args.out_dir: df["out_dir"] = args.out_dir df_list = csv2list(df) with get_pool(args.n_cpu) as pool: df_list_out = tqdm_parallel_imap(process_row, df_list, pool) df_out = pd.DataFrame(df_list_out) df_out.to_csv(args.out_csv, index=False)
def optimize_thresholds( predictions: np.ndarray, labels: np.ndarray, classes: List[int], metric_fn: Callable = metrics.roc_auc_score, num_splits: int = 5, num_repeats: int = 1, num_workers: int = 0, ignore_label: int = None, ) -> Tuple[Dict, Dict]: """@TODO: Docs. Contribution is welcome.""" pool = utils.get_pool(num_workers) predictions_copy = predictions.copy() predictions_list, labels_list = [], [] for class_index in classes: predictions_list.append(predictions_copy[:, class_index]) labels_list.append( get_binary_labels(labels, class_index, ignore_label=ignore_label) ) results = utils.tqdm_parallel_imap( find_best_threshold_wrapper, zip( classes, predictions_list, labels_list, repeat(metric_fn), repeat(num_splits), repeat(num_repeats), ), pool, ) results = [(r[1], r[2]) for r in sorted(results, key=lambda x: x[0])] result_thresholds = [r[0] for r in results] result_metrics = [r[1] for r in results] class_thresholds = {c: t for (c, t) in zip(classes, result_thresholds)} class_metrics = {c: m for (c, m) in zip(classes, result_metrics)} return class_thresholds, class_metrics