Merge branch 'main' of https://github.com/Kitware/batbot into tas/fast-spectrogram

Author: trevor.stout

README.rst

@@ -2,7 +2,7 @@
 Kitware BatBot
 ==============
 
-|Tests| |Codecov| |Wheel| |Docker| |ReadTheDocs| |Huggingface|
+|Tests| |Codecov| |Wheel| |Docker| |ReadTheDocs|
 
 .. image:: https://github.com/Kitware/batbot/raw/main/assets/logo.png
    :alt: Batbot
@@ -312,7 +312,3 @@ The code base has been formatted by `Black <https://black.readthedocs.io/en/stab
 .. |ReadTheDocs| image:: https://readthedocs.org/projects/batbot/badge/?version=latest
     :target: https://kitware-batbot.readthedocs.io/en/latest/?badge=latest
     :alt: ReadTheDocs
-
-.. |Huggingface| image:: https://img.shields.io/badge/HuggingFace-running-success
-    :target: https://huggingface.co/spaces/Kitware/batbot
-    :alt: Huggingface

batbot/__init__.py

@@ -19,7 +19,7 @@
 
 import concurrent.futures
 from multiprocessing import Manager
-from os.path import exists, join, split, splitext
+from os.path import exists, join, split, splitext, basename
 from pathlib import Path
 
 import pooch
@@ -301,8 +301,9 @@ def example():
 
     import time
 
+    output_stem = join('output', splitext(basename(wav_filepath))[0])
     start_time = time.time()
-    results = pipeline(wav_filepath, fast_mode=False, force_overwrite=True)
+    results = pipeline(wav_filepath, out_file_stem=output_stem, fast_mode=False, force_overwrite=True)
     stop_time = time.time()
     print('Example pipeline completed in {} seconds.'.format(stop_time - start_time))
 

batbot/batbot.py

@@ -56,16 +56,17 @@ def fetch(config):
     type=str,
     callback=pipeline_filepath_validator,
 )
-@click.option(
-    '--config',
-    help='Which ML model to use for inference',
-    default=None,
-    type=click.Choice(['usgs']),
-)
+# @click.option(
+#     '--config',
+#     help='Which ML model to use for inference',
+#     default=None,
+#     type=click.Choice(['usgs']),
+# )
 @click.option(
     '--output',
-    help='Path to output JSON (if unspecified, results are printed to screen)',
-    default=None,
+    'output_path',
+    help='Path to output folder for the results',
+    default='.',
     type=str,
 )
 # @click.option(
@@ -76,45 +77,21 @@ def fetch(config):
 # )
 def pipeline(
     filepath,
-    config,
-    output,
+    # config,
+    output_path,
     # classifier_thresh,
 ):
-    """
-    Run the BatBot pipeline on an input WAV filepath.  An example output of the JSON
-    can be seen below.
-
-    .. code-block:: javascript
 
-            {
-                '/path/to/file.wav': {
-                    'classifier': 0.5,
-                }
-            }
-    """
-    if config is not None:
-        config = config.strip().lower()
-    # classifier_thresh /= 100.0
+    # define out file stem using given output folder
+    out_file_stem = join(output_path, splitext(basename(filepath))[0])
 
-    score = batbot.pipeline(
+    batbot.pipeline(
         filepath,
-        config=config,
+        # config=config,
         # classifier_thresh=classifier_thresh,
+        out_file_stem=out_file_stem,
     )
 
-    data = {
-        filepath: {
-            'classifier': score,
-        }
-    }
-
-    log.debug('Outputting results...')
-    if output:
-        with open(output, 'w') as outfile:
-            json.dump(data, outfile, indent=4)
-    else:
-        print(data)
-
 
 @click.command('preprocess')
 @click.argument(

batbot/spectrogram/__init__.py

@@ -1432,7 +1432,12 @@ def compute_wrapper(
 
     chunksize = int(50e3)
 
-    debug_path = get_debug_path(split(out_file_stem)[0], wav_filepath, enabled=debug)
+    output_folder = split(out_file_stem)[0]
+    debug_path = get_debug_path(output_folder, wav_filepath, enabled=debug)
+    # create output folder if it doesn't exist
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+        assert exists(output_folder)
 
     # Load the spectrogram from a WAV file on disk
     with warnings.catch_warnings():
@@ -1867,12 +1872,10 @@ def compute_wrapper(
         'segments': metas,
     }
     if 'stft_db' in segments:
-        metadata['size']['compressed'] = (
-            {
-                'width.px': segments['stft_db'].shape[1],
-                'height.px': segments['stft_db'].shape[0],
-            },
-        )
+        metadata['size']['compressed'] = {
+            'width.px': segments['stft_db'].shape[1],
+            'height.px': segments['stft_db'].shape[0],
+        }
 
     metadata_path = f'{out_file_stem}.metadata.json'
     with open(metadata_path, 'w') as metafile:

tests/test_spectrogram.py

@@ -5,4 +5,5 @@ def test_spectrogram_compute():
     from batbot.spectrogram import compute
 
     wav_filepath = abspath(join('examples', 'example2.wav'))
-    output_paths, metadata_path, metadata = compute(wav_filepath)
+    output_folder = './output'
+    output_paths, metadata_path, metadata = compute(wav_filepath, output_folder=output_folder)