-
Notifications
You must be signed in to change notification settings - Fork 2
/
preprocessing.py
36 lines (27 loc) · 1.35 KB
/
preprocessing.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
from ddsp.training.preprocessing import Preprocessor, DefaultPreprocessor, at_least_3d
import ddsp
import tensorflow.compat.v2 as tf
class MidiPreprocessor(Preprocessor):
"""Default class that resamples features and adds `f0_hz` key."""
def __init__(self, n_timesteps=1000):
super().__init__()
self.n_timesteps = n_timesteps
self.df_pp = DefaultPreprocessor(time_steps=n_timesteps)
def __call__(self, features, training=True):
super().__call__(features, training)
return self._default_processing(features)
def _default_processing(self, features):
"""Always resample to `n_timesteps` and scale 'loudness_db' and 'f0_hz'."""
# apply preprocesssing (scale loudness and f0, make sure batch dim exists etc..)
if "loudness_db" in features and "f0_hz" in features:
features = self.df_pp(features)
for k in ['midi_velocity', 'midi_pitch']:
features[k] = at_least_3d(features[k])
features[k] = ddsp.core.resample(
features[k], n_timesteps=self.n_timesteps)
# relu is here to fix an issue in the dataset preparation
features["midi_velocity_scaled"] = tf.nn.relu(
features["midi_velocity"]/127.0)
features["midi_pitch_scaled"] = tf.nn.relu(
features["midi_pitch"]/127.0)
return features