cog-ified

Author: ericguizzo

cog.yaml

@@ -0,0 +1,18 @@
+build:
+  python_version: "3.6"
+  gpu: false
+  python_packages:
+    - pandas==1.1.5
+    - numpy==1.17.3
+    - wave==0.0.2
+    - sklearn==0.0
+    - librosa==0.6.3
+    - soundfile==0.9.0
+    - tqdm==4.28.1
+    - matplotlib==2.2.3
+    - pyaudio==0.2.11
+    - numba==0.48
+  system_packages:
+    - "ffmpeg"
+    - "portaudio19-dev"
+predict: "predict.py:EmoPredictor"

create_csv.py

@@ -69,18 +69,20 @@ def write_tess_ravdess_csv(emotions=["sad", "neutral", "happy"], train_name="tra
 
     for category in emotions:
         # for training speech directory
-        for i, path in enumerate(glob.glob(f"data/training/Actor_*/*_{category}.wav")):
+        total_files = glob.glob(f"data/training/Actor_*/*_{category}.wav")
+        for i, path in enumerate(total_files):
             train_target["path"].append(path)
             train_target["emotion"].append(category)
-        if verbose:
-            print(f"[TESS&RAVDESS] There are {i} training audio files for category:{category}")
+        if verbose and total_files:
+            print(f"[TESS&RAVDESS] There are {len(total_files)} training audio files for category:{category}")
 
         # for validation speech directory
-        for i, path in enumerate(glob.glob(f"data/validation/Actor_*/*_{category}.wav")):
+        total_files = glob.glob(f"data/validation/Actor_*/*_{category}.wav")
+        for i, path in enumerate(total_files):
             test_target["path"].append(path)
             test_target["emotion"].append(category)
-        if verbose:
-            print(f"[TESS&RAVDESS] There are {i} testing audio files for category:{category}")
+        if verbose and total_files:
+            print(f"[TESS&RAVDESS] There are {len(total_files)} testing audio files for category:{category}")
     pd.DataFrame(test_target).to_csv(test_name)
     pd.DataFrame(train_target).to_csv(train_name)
 

deep_emotion_recognition.py

@@ -3,26 +3,13 @@
 import sys
 stderr = sys.stderr
 sys.stderr = open(os.devnull, 'w')
-import keras
-sys.stderr = stderr
-# to use CPU uncomment below code
-os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"   # see issue #152
-os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
-# disable tensorflow logs
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 import tensorflow as tf
 
-config = tf.ConfigProto(intra_op_parallelism_threads=5,
-                        inter_op_parallelism_threads=5, 
-                        allow_soft_placement=True,
-                        device_count = {'CPU' : 1,
-                                        'GPU' : 0}
-                       )
-from keras.layers import LSTM, GRU, Dense, Activation, LeakyReLU, Dropout
-from keras.layers import Conv1D, MaxPool1D, GlobalAveragePooling1D
-from keras.models import Sequential
-from keras.callbacks import ModelCheckpoint, TensorBoard
-from keras.utils import to_categorical
+from tensorflow.keras.layers import LSTM, GRU, Dense, Activation, LeakyReLU, Dropout
+from tensorflow.keras.layers import Conv1D, MaxPool1D, GlobalAveragePooling1D
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.callbacks import ModelCheckpoint, TensorBoard
+from tensorflow.keras.utils import to_categorical
 
 from sklearn.metrics import accuracy_score, mean_absolute_error, confusion_matrix
 
@@ -264,7 +251,7 @@ def train(self, override=False):
         model_filename = self._get_model_filename()
 
         self.checkpointer = ModelCheckpoint(model_filename, save_best_only=True, verbose=1)
-        self.tensorboard = TensorBoard(log_dir=f"logs/{self.model_name}")
+        self.tensorboard = TensorBoard(log_dir=os.path.join("logs", self.model_name))
 
         self.history = self.model.fit(self.X_train, self.y_train,
                         batch_size=self.batch_size,

emotion_recognition.py

@@ -182,7 +182,7 @@ def predict_proba(self, audio_path):
             feature = extract_feature(audio_path, **self.audio_config).reshape(1, -1)
             proba = self.model.predict_proba(feature)[0]
             result = {}
-            for emotion, prob in zip(self.emotions, proba):
+            for emotion, prob in zip(self.model.classes_, proba):
                 result[emotion] = prob
             return result
         else: