-
-
Notifications
You must be signed in to change notification settings - Fork 38
/
export.py
147 lines (131 loc) · 5.34 KB
/
export.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
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import argparse
import numpy as np
import json
import torch
import os
from model import PedalNet
def convert(args):
"""
Converts a *.ckpt model from PedalNet into a .json format used in WaveNetVA.
Current changes to the original PedalNet model to match WaveNetVA include:
1. Added CausalConv1d() to use causal padding
2. Added an input layer, which is a Conv1d(in_channls=1, out_channels=num_channels, kernel_size=1)
3. Instead of two conv_stacks for tanh and sigm, used a single hidden layer with input_channels=16,
output_channels=32, then split the matrix for tanh and sigm calculation.
Note: The original PedalNet model was intended for use on PCM Int16 format wave files. The WaveNetVA is
intended as a plugin, which processes float32 audio data. The PedalNet model must be trained on wave files
saved as Float32 data, which has sample data in the range -1 to 1.
Note: The WaveNetVA plugin doesn't perform the standardization step as in predict.py. With the standardization step
omitted, the signals match between the plugin with converted model, and the predict.py output.
The model parameters used for conversion testing match the Wavenetva1 model (limited testing using other parameters):
--num_channels=16, --dilation_depth=10, --num_repeat=1, --kernel_size=3
"""
# Permute tensors to match Tensorflow format with .permute(a,b,c):
a, b, c = (
2,
1,
0,
) # Pytorch uses (out_channels, in_channels, kernel_size), TensorFlow uses (kernel_size, in_channels, out_channels)
model = PedalNet.load_from_checkpoint(checkpoint_path=args.model)
sd = model.state_dict()
# Get hparams from model
hparams = model.hparams
residual_channels = hparams.num_channels
filter_width = hparams.kernel_size
dilations = [2 ** d for d in range(hparams.dilation_depth)] * hparams.num_repeat
data_out = {
"activation": "gated",
"output_channels": 1,
"input_channels": 1,
"residual_channels": residual_channels,
"filter_width": filter_width,
"dilations": dilations,
"variables": [],
}
# Use pytorch model data to populate the json data for each layer
for i in range(-1, len(dilations) + 1):
# Input Layer
if i == -1:
data_out["variables"].append(
{
"layer_idx": i,
"data": [
str(w) for w in (sd["wavenet.input_layer.weight"]).permute(a, b, c).flatten().numpy().tolist()
],
"name": "W",
}
)
data_out["variables"].append(
{
"layer_idx": i,
"data": [str(b) for b in (sd["wavenet.input_layer.bias"]).flatten().numpy().tolist()],
"name": "b",
}
)
# Linear Mix Layer
elif i == len(dilations):
data_out["variables"].append(
{
"layer_idx": i,
"data": [
str(w) for w in (sd["wavenet.linear_mix.weight"]).permute(a, b, c).flatten().numpy().tolist()
],
"name": "W",
}
)
data_out["variables"].append(
{
"layer_idx": i,
"data": [str(b) for b in (sd["wavenet.linear_mix.bias"]).numpy().tolist()],
"name": "b",
}
)
# Hidden Layers
else:
data_out["variables"].append(
{
"layer_idx": i,
"data": [
str(w)
for w in sd["wavenet.hidden." + str(i) + ".weight"].permute(a, b, c).flatten().numpy().tolist()
],
"name": "W_conv",
}
)
data_out["variables"].append(
{
"layer_idx": i,
"data": [str(b) for b in sd["wavenet.hidden." + str(i) + ".bias"].flatten().numpy().tolist()],
"name": "b_conv",
}
)
data_out["variables"].append(
{
"layer_idx": i,
"data": [
str(w2)
for w2 in sd["wavenet.residuals." + str(i) + ".weight"]
.permute(a, b, c)
.flatten()
.numpy()
.tolist()
],
"name": "W_out",
}
)
data_out["variables"].append(
{
"layer_idx": i,
"data": [str(b2) for b2 in sd["wavenet.residuals." + str(i) + ".bias"].flatten().numpy().tolist()],
"name": "b_out",
}
)
# output final dictionary to json file
with open(args.model.replace(".ckpt", ".json"), "w") as outfile:
json.dump(data_out, outfile)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model", default="models/pedalnet/pedalnet.ckpt")
parser.add_argument("--format", default="json")
args = parser.parse_args()
convert(args)