File size: 10,018 Bytes
64db264
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "starganv2_vc_weights_converter.ipynb",
      "private_outputs": true,
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "CA5i7YAlagUA"
      },
      "outputs": [],
      "source": [
        "!git clone https://github.com/yl4579/StarGANv2-VC\n",
        "!pip install SoundFile torchaudio munch\n",
        "!git clone https://github.com/HighCWu/starganv2vc-paddle\n",
        "!cd starganv2vc-paddle && pip install paddlepaddle-gpu==2.2.2 paddleaudio munch pydub\n",
        "!cp -r starganv2vc-paddle/starganv2vc_paddle StarGANv2-VC/"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!gdown https://drive.google.com/uc?id=1nzTyyl-9A1Hmqya2Q_f2bpZkUoRjbZsY"
      ],
      "metadata": {
        "id": "ac4g4L1Bbx1t"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip -qq Models.zip\n",
        "!rm -rf Models.zip\n",
        "!mv Models StarGANv2-VC/Models"
      ],
      "metadata": {
        "id": "EJ3vG_RvcOD8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%cd StarGANv2-VC"
      ],
      "metadata": {
        "id": "rKovh1Egi4mJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import yaml\n",
        "import numpy as np\n",
        "import torch\n",
        "import warnings\n",
        "warnings.simplefilter('ignore')\n",
        "\n",
        "from munch import Munch\n",
        "\n",
        "from models import build_model\n",
        "\n",
        "from Utils.ASR.models import ASRCNN\n",
        "from Utils.JDC.model import JDCNet\n",
        "\n",
        "torch.backends.cudnn.benchmark = True #\n",
        "\n",
        "def main(config_path):\n",
        "    config = yaml.safe_load(open(config_path))\n",
        "    \n",
        "    device = config.get('device', 'cpu')\n",
        "\n",
        "    # load pretrained ASR model\n",
        "    ASR_config = config.get('ASR_config', False)\n",
        "    ASR_path = config.get('ASR_path', False)\n",
        "    with open(ASR_config) as f:\n",
        "            ASR_config = yaml.safe_load(f)\n",
        "    ASR_model_config = ASR_config['model_params']\n",
        "    ASR_model = ASRCNN(**ASR_model_config)\n",
        "    params = torch.load(ASR_path, map_location='cpu')['model']\n",
        "    ASR_model.load_state_dict(params)\n",
        "    ASR_model.to(device)\n",
        "    _ = ASR_model.eval()\n",
        "    \n",
        "    # load pretrained F0 model\n",
        "    F0_path = config.get('F0_path', False)\n",
        "    F0_model = JDCNet(num_class=1, seq_len=192)\n",
        "    params = torch.load(F0_path, map_location='cpu')['net']\n",
        "    F0_model.load_state_dict(params)\n",
        "    F0_model.to(device)\n",
        "    \n",
        "    # build model\n",
        "    _, model_ema = build_model(Munch(config['model_params']), F0_model, ASR_model)\n",
        "    pretrained_path = 'Models/epoch_00150.pth'# config.get('pretrained_model', False)\n",
        "    params = torch.load(pretrained_path, map_location='cpu')['model_ema']\n",
        "    [model_ema[key].load_state_dict(state_dict) for key, state_dict in params.items()]\n",
        "    _ = [model_ema[key].to(device) for key in model_ema]\n",
        "\n",
        "    return ASR_model, F0_model, model_ema\n",
        "\n",
        "ASR_model_torch, F0_model_torch, model_ema_torch = main('./Models/config.yml')\n"
      ],
      "metadata": {
        "id": "UpMuk5kni67B"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import yaml\n",
        "import numpy as np\n",
        "import paddle\n",
        "import warnings\n",
        "warnings.simplefilter('ignore')\n",
        "\n",
        "from munch import Munch\n",
        "\n",
        "from starganv2vc_paddle.models import build_model\n",
        "\n",
        "from starganv2vc_paddle.Utils.ASR.models import ASRCNN\n",
        "from starganv2vc_paddle.Utils.JDC.model import JDCNet\n",
        "\n",
        "@paddle.no_grad()\n",
        "def convert_weights(torch_model, paddle_model):\n",
        "    _ = torch_model.eval()\n",
        "    _ = paddle_model.eval()\n",
        "    dense_layers = []\n",
        "    for name, layer in torch_model.named_modules():\n",
        "        if isinstance(layer, torch.nn.Linear):\n",
        "            dense_layers.append(name)\n",
        "    torch_state_dict = torch_model.state_dict()\n",
        "    for name, param in paddle_model.named_parameters():\n",
        "        name = name.replace('._mean', '.running_mean')\n",
        "        name = name.replace('._variance', '.running_var')\n",
        "        name = name.replace('.scale', '.weight')\n",
        "        target_param = torch_state_dict[name].detach().cpu().numpy()\n",
        "        if '.'.join(name.split('.')[:-1]) in dense_layers:\n",
        "            if len(param.shape) == 2:\n",
        "                target_param = target_param.transpose((1,0))\n",
        "        param.set_value(paddle.to_tensor(target_param))\n",
        "\n",
        "@torch.no_grad()\n",
        "@paddle.no_grad()\n",
        "def main(config_path):\n",
        "    config = yaml.safe_load(open(config_path))\n",
        "    \n",
        "    ASR_config = config.get('ASR_config', False)\n",
        "    with open(ASR_config) as f:\n",
        "            ASR_config = yaml.safe_load(f)\n",
        "    ASR_model_config = ASR_config['model_params']\n",
        "    ASR_model = ASRCNN(**ASR_model_config)\n",
        "    _ = ASR_model.eval()\n",
        "    convert_weights(ASR_model_torch, ASR_model)\n",
        "\n",
        "    F0_model = JDCNet(num_class=1, seq_len=192)\n",
        "    _ = F0_model.eval()\n",
        "    convert_weights(F0_model_torch, F0_model)\n",
        "    \n",
        "    # build model\n",
        "    model, model_ema = build_model(Munch(config['model_params']), F0_model, ASR_model)\n",
        "\n",
        "    asr_input = paddle.randn([2, 80, 192])\n",
        "    asr_output = ASR_model(asr_input)\n",
        "    asr_output_torch = ASR_model_torch(torch.from_numpy(asr_input.numpy()).cuda())\n",
        "    print('ASR model input:', asr_input.shape, 'output:', asr_output.shape)\n",
        "    print('Error:', (asr_output_torch.cpu().numpy() - asr_output.numpy()).mean())\n",
        "    mel_input = paddle.randn([2, 1, 192, 512])\n",
        "    f0_output = F0_model(mel_input)\n",
        "    f0_output_torch = F0_model_torch(torch.from_numpy(mel_input.numpy()).cuda())\n",
        "    print('F0 model input:', mel_input.shape, 'output:', [t.shape for t in f0_output])\n",
        "    # print('Error:', (t_dict2['output'].cpu().numpy() - t_dict1['output'].numpy()).mean())\n",
        "    print('Error:', [(t1.cpu().numpy() - t2.numpy()).mean() for t1, t2 in zip(f0_output_torch, f0_output)])\n",
        "\n",
        "    _ = [convert_weights(model_ema_torch[k], model_ema[k]) for k in model_ema.keys()]\n",
        "    label = paddle.to_tensor([0,0], dtype=paddle.int64)\n",
        "    latent_dim = model_ema.mapping_network.shared[0].weight.shape[0]\n",
        "    latent_style = paddle.randn([2, latent_dim])\n",
        "    ref = model_ema.mapping_network(latent_style, label)\n",
        "    ref_torch = model_ema_torch.mapping_network(torch.from_numpy(latent_style.numpy()).cuda(), torch.from_numpy(label.numpy()).cuda())\n",
        "    print('Error of mapping network:', (ref_torch.cpu().numpy() - ref.numpy()).mean())\n",
        "    mel_input2 = paddle.randn([2, 1, 192, 512])\n",
        "    style_ref = model_ema.style_encoder(mel_input2, label)\n",
        "    style_ref_torch = model_ema_torch.style_encoder(torch.from_numpy(mel_input2.numpy()).cuda(), torch.from_numpy(label.numpy()).cuda())\n",
        "    print('StyleGANv2-VC encoder inputs:', mel_input2.shape, 'output:', style_ref.shape, 'should has the same shape as the ref:', ref.shape)\n",
        "    print('Error of style encoder:', (style_ref_torch.cpu().numpy() - style_ref.numpy()).mean())\n",
        "    f0_feat = F0_model.get_feature_GAN(mel_input)\n",
        "    f0_feat_torch = F0_model_torch.get_feature_GAN(torch.from_numpy(mel_input.numpy()).cuda())\n",
        "    print('Error of f0 feat:', (f0_feat_torch.cpu().numpy() - f0_feat.numpy()).mean())\n",
        "    out = model_ema.generator(mel_input, style_ref, F0=f0_feat)\n",
        "    out_torch = model_ema_torch.generator(torch.from_numpy(mel_input.numpy()).cuda(), torch.from_numpy(style_ref.numpy()).cuda(), F0=torch.from_numpy(f0_feat.numpy()).cuda())\n",
        "    print('StyleGANv2-VC inputs:', label.shape, latent_style.shape, mel_input.shape, 'output:', out.shape)\n",
        "    print('Error:', (out_torch.cpu().numpy() - out.numpy()).mean())\n",
        "\n",
        "    paddle.save({'model': ASR_model.state_dict()}, 'ASR.pd')\n",
        "    paddle.save({ 'net': F0_model.state_dict()}, 'F0.pd')\n",
        "    model_ema_dict = {key: model.state_dict() for key, model in model_ema.items()}\n",
        "    \n",
        "    paddle.save({ 'model_ema': model_ema_dict }, 'VC.pd')\n",
        "\n",
        "    return 0\n",
        "\n",
        "main('./Models/config.yml')\n"
      ],
      "metadata": {
        "id": "PnuApVuyIIyd"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}