tfrecords wip

speech_data.py

@@ -90,6 +90,39 @@ def create_spectrogram_data(audio_group='audio'):
     audio_samples['window_count'] = audio_samples.loc[:,'spectrogram'].apply(lambda x: x.shape[0])
     audio_samples.to_pickle('outputs/{}-spectrogram.pkl'.format(audio_group))
 
+def create_spectrogram_tfrecords(audio_group='audio'):
+    audio_samples = pd.read_csv( './outputs/' + audio_group + '.csv'
+        , names=['word','phonemes', 'voice', 'language', 'rate', 'variant', 'file']
+        , quoting=csv.QUOTE_NONE)
+    # audio_samples = audio_samples.loc[audio_samples['word'] ==
+    #                                   'sunflowers'].reset_index(drop=True)
+    audio_samples['file_paths'] = audio_samples.loc[:, 'file'].apply(lambda x: 'outputs/' + audio_group + '/' + x)
+    audio_samples['file_exists'] = apply_by_multiprocessing(audio_samples['file_paths'], os.path.exists)
+    audio_samples = audio_samples[audio_samples['file_exists'] == True].reset_index()
+    # audio_samples['spectrogram'] = apply_by_multiprocessing(audio_samples['file_paths'],generate_aiff_spectrogram)#.apply(
+    # audio_samples['window_count'] = audio_samples.loc[:,'spectrogram'].apply(lambda x: x.shape[0])
+    # audio_samples.to_pickle('outputs/{}-spectrogram.pkl'.format(audio_group))
+
+    def _float_feature(value):
+      return tf.train.Feature(float_list=tf.train.FloatList(value=value))
+
+    def _int64_feature(value):
+      return tf.train.Feature(int64_list=tf.train.Int64List(value=value))
+
+    def _bytes_feature(value):
+      return tf.train.Feature(bytes_list=tf.train.BytesList(value=value))
+    writer = tf.python_io.TFRecordWriter(output_path)
+
+    for sample in audio_samples:
+        example = tf.train.Example(features=tf.train.Features(
+          feature={
+            'label': _int64_feature([label]),
+            'path': _bytes_feature([image_path]),
+            'instance' : _bytes_feature([instance_id])
+          }
+        ))
+    writer.write(example.SerializeToString())
+    writer.close()
 
 def create_tagged_data(audio_samples):
     same_data, diff_data = [], []