Small fixes

.gitignore

@@ -1,3 +1,7 @@
+# Local testing
+playground*
+foo*
+
 # Apple :/
 .DS_Store
 

analyze.py

@@ -4,10 +4,10 @@
 import argparse
 import datetime
 import json
+import multiprocessing
 import operator
 import os
 import sys
-import multiprocessing
 from multiprocessing import Pool, freeze_support
 
 import numpy as np

model.py

@@ -333,10 +333,11 @@ def saveLinearClassifier(classifier, model_path: str, labels: list[str], mode="r
 
 
 def save_raven_model(classifier, model_path, labels: list[str], mode="replace"):
-    import tensorflow as tf
     import csv
     import json
 
+    import tensorflow as tf
+
     global PBMODEL
 
     tf.get_logger().setLevel("ERROR")

requirements.txt

@@ -0,0 +1,8 @@
+librosa==0.9.2
+resampy
+tensorflow==2.15.0
+gradio
+webview
+tqdm
+bottle
+requests

segments.py

@@ -3,8 +3,8 @@
 Can be used to save the segments of the audio files for each detection.
 """
 import argparse
-import os
 import multiprocessing
+import os
 from multiprocessing import Pool
 
 import numpy as np

train.py

@@ -3,19 +3,20 @@
 Can be used to train a custom classifier with new training data.
 """
 import argparse
-import os
-import tqdm
 import multiprocessing
+import os
 from functools import partial
 from multiprocessing.pool import Pool
 
 import numpy as np
+import tqdm
 
 import audio
 import config as cfg
 import model
 import utils
 
+
 def _loadAudioFile(f, label_vector, config):
     """Load an audio file and extract features.
     Args:
@@ -40,7 +41,7 @@ def _loadAudioFile(f, label_vector, config):
     except Exception as e:
         # Print Error
         print(f"\t Error when loading file {f}", flush=True)
-        pass
+        return np.array([]), np.array([])
 
     # Crop training samples
     if cfg.SAMPLE_CROP_MODE == "center":
@@ -208,10 +209,11 @@ def trainModel(on_epoch_end=None, on_trial_result=None, on_data_load_end=None):
     print(f"...Done. Loaded {x_train.shape[0]} training samples and {y_train.shape[1]} labels.", flush=True)
 
     if cfg.AUTOTUNE:
-        import keras_tuner
-        import keras
         import gc
 
+        import keras
+        import keras_tuner
+
         # Call callback to initialize progress bar
         if on_trial_result:
             on_trial_result(0)

utils.py

@@ -2,9 +2,10 @@
 """
 import os
 import traceback
-import numpy as np
 from pathlib import Path
 
+import numpy as np
+
 import config as cfg