params['path_centers'],
FORCE_RELOAD)
df_eval = df_paths.copy(deep=True)
for stage in params['stages']:
df_eval = evaluate_detection_stage(df_eval, stage,
params['path_infofile'],
params['path_expt'],
params['nb_workers'])
if not df_eval.empty and 'image' in df_eval.columns:
df_eval.set_index('image', inplace=True)
df_eval.to_csv(os.path.join(params['path_expt'],
NAME_CSV_TRIPLES_STAT))
gc.collect()
time.sleep(1)
if not df_eval.empty:
df_stat = df_eval.describe().transpose()
logging.info('STATISTIC: \n %r', df_stat)
df_stat.to_csv(os.path.join(params['path_expt'], NAME_CSV_STATISTIC))
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG)
logging.info('running...')
params = run_train.arg_parse_params(DEFAULT_PARAMS)
main(params)
logging.info('DONE')
tqdm_bar = tqdm.tqdm(total=len(df_paths))
if params['nb_jobs'] > 1:
wrapper_clustering = partial(cluster_points_draw_export,
params=params,
path_out=params['path_output'])
pool = mproc.Pool(params['nb_jobs'])
for dict_center in pool.imap_unordered(
wrapper_clustering,
(dict(row) for idx, row in df_paths.iterrows())):
df_paths_new = df_paths_new.append(dict_center, ignore_index=True)
tqdm_bar.update()
pool.close()
pool.join()
else:
for dict_row in (dict(row) for idx, row in df_paths.iterrows()):
dict_center = cluster_points_draw_export(dict_row, params,
params['path_output'])
df_paths_new = df_paths_new.append(dict_center, ignore_index=True)
tqdm_bar.update()
df_paths_new.set_index('image', inplace=True)
df_paths_new.to_csv(path_cover)
logging.info('DONE')
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG)
params = run_train.arg_parse_params(PARAMS)
main(params)
