File size: 8,771 Bytes
31f2f28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
from os.path import dirname, join, basename, isfile
from tqdm import tqdm

from models import SyncNet_color as SyncNet
import audio

import torch
from torch import nn
from torch import optim
import torch.backends.cudnn as cudnn
from torch.utils import data as data_utils
import numpy as np

from glob import glob

import os, random, cv2, argparse
from hparams import hparams, get_image_list

parser = argparse.ArgumentParser(description='Code to train the expert lip-sync discriminator')

parser.add_argument("--data_root", help="Root folder of the preprocessed LRS2 dataset", required=True)

parser.add_argument('--checkpoint_dir', help='Save checkpoints to this directory', required=True, type=str)
parser.add_argument('--checkpoint_path', help='Resumed from this checkpoint', default=None, type=str)

args = parser.parse_args()


global_step = 0
global_epoch = 0
use_cuda = torch.cuda.is_available()
print('use_cuda: {}'.format(use_cuda))

syncnet_T = 5
syncnet_mel_step_size = 16

class Dataset(object):
    def __init__(self, split):
        self.all_videos = get_image_list(args.data_root, split)

    def get_frame_id(self, frame):
        return int(basename(frame).split('.')[0])

    def get_window(self, start_frame):
        start_id = self.get_frame_id(start_frame)
        vidname = dirname(start_frame)

        window_fnames = []
        for frame_id in range(start_id, start_id + syncnet_T):
            frame = join(vidname, '{}.jpg'.format(frame_id))
            if not isfile(frame):
                return None
            window_fnames.append(frame)
        return window_fnames

    def crop_audio_window(self, spec, start_frame):
        # num_frames = (T x hop_size * fps) / sample_rate
        start_frame_num = self.get_frame_id(start_frame)
        start_idx = int(80. * (start_frame_num / float(hparams.fps)))

        end_idx = start_idx + syncnet_mel_step_size

        return spec[start_idx : end_idx, :]


    def __len__(self):
        return len(self.all_videos)

    def __getitem__(self, idx):
        while 1:
            idx = random.randint(0, len(self.all_videos) - 1)
            vidname = self.all_videos[idx]

            img_names = list(glob(join(vidname, '*.jpg')))
            if len(img_names) <= 3 * syncnet_T:
                continue
            img_name = random.choice(img_names)
            wrong_img_name = random.choice(img_names)
            while wrong_img_name == img_name:
                wrong_img_name = random.choice(img_names)

            if random.choice([True, False]):
                y = torch.ones(1).float()
                chosen = img_name
            else:
                y = torch.zeros(1).float()
                chosen = wrong_img_name

            window_fnames = self.get_window(chosen)
            if window_fnames is None:
                continue

            window = []
            all_read = True
            for fname in window_fnames:
                img = cv2.imread(fname)
                if img is None:
                    all_read = False
                    break
                try:
                    img = cv2.resize(img, (hparams.img_size, hparams.img_size))
                except Exception as e:
                    all_read = False
                    break

                window.append(img)

            if not all_read: continue

            try:
                wavpath = join(vidname, "audio.wav")
                wav = audio.load_wav(wavpath, hparams.sample_rate)

                orig_mel = audio.melspectrogram(wav).T
            except Exception as e:
                continue

            mel = self.crop_audio_window(orig_mel.copy(), img_name)

            if (mel.shape[0] != syncnet_mel_step_size):
                continue

            # H x W x 3 * T
            x = np.concatenate(window, axis=2) / 255.
            x = x.transpose(2, 0, 1)
            x = x[:, x.shape[1]//2:]

            x = torch.FloatTensor(x)
            mel = torch.FloatTensor(mel.T).unsqueeze(0)

            return x, mel, y

logloss = nn.BCELoss()
def cosine_loss(a, v, y):
    d = nn.functional.cosine_similarity(a, v)
    loss = logloss(d.unsqueeze(1), y)

    return loss

def train(device, model, train_data_loader, test_data_loader, optimizer,
          checkpoint_dir=None, checkpoint_interval=None, nepochs=None):

    global global_step, global_epoch
    resumed_step = global_step
    
    while global_epoch < nepochs:
        running_loss = 0.
        prog_bar = tqdm(enumerate(train_data_loader))
        for step, (x, mel, y) in prog_bar:
            model.train()
            optimizer.zero_grad()

            # Transform data to CUDA device
            x = x.to(device)

            mel = mel.to(device)

            a, v = model(mel, x)
            y = y.to(device)

            loss = cosine_loss(a, v, y)
            loss.backward()
            optimizer.step()

            global_step += 1
            cur_session_steps = global_step - resumed_step
            running_loss += loss.item()

            if global_step == 1 or global_step % checkpoint_interval == 0:
                save_checkpoint(
                    model, optimizer, global_step, checkpoint_dir, global_epoch)

            if global_step % hparams.syncnet_eval_interval == 0:
                with torch.no_grad():
                    eval_model(test_data_loader, global_step, device, model, checkpoint_dir)

            prog_bar.set_description('Loss: {}'.format(running_loss / (step + 1)))

        global_epoch += 1

def eval_model(test_data_loader, global_step, device, model, checkpoint_dir):
    eval_steps = 1400
    print('Evaluating for {} steps'.format(eval_steps))
    losses = []
    while 1:
        for step, (x, mel, y) in enumerate(test_data_loader):

            model.eval()

            # Transform data to CUDA device
            x = x.to(device)

            mel = mel.to(device)

            a, v = model(mel, x)
            y = y.to(device)

            loss = cosine_loss(a, v, y)
            losses.append(loss.item())

            if step > eval_steps: break

        averaged_loss = sum(losses) / len(losses)
        print(averaged_loss)

        return

def save_checkpoint(model, optimizer, step, checkpoint_dir, epoch):

    checkpoint_path = join(
        checkpoint_dir, "checkpoint_step{:09d}.pth".format(global_step))
    optimizer_state = optimizer.state_dict() if hparams.save_optimizer_state else None
    torch.save({
        "state_dict": model.state_dict(),
        "optimizer": optimizer_state,
        "global_step": step,
        "global_epoch": epoch,
    }, checkpoint_path)
    print("Saved checkpoint:", checkpoint_path)

def _load(checkpoint_path):
    if use_cuda:
        checkpoint = torch.load(checkpoint_path)
    else:
        checkpoint = torch.load(checkpoint_path,
                                map_location=lambda storage, loc: storage)
    return checkpoint

def load_checkpoint(path, model, optimizer, reset_optimizer=False):
    global global_step
    global global_epoch

    print("Load checkpoint from: {}".format(path))
    checkpoint = _load(path)
    model.load_state_dict(checkpoint["state_dict"])
    if not reset_optimizer:
        optimizer_state = checkpoint["optimizer"]
        if optimizer_state is not None:
            print("Load optimizer state from {}".format(path))
            optimizer.load_state_dict(checkpoint["optimizer"])
    global_step = checkpoint["global_step"]
    global_epoch = checkpoint["global_epoch"]

    return model

if __name__ == "__main__":
    checkpoint_dir = args.checkpoint_dir
    checkpoint_path = args.checkpoint_path

    if not os.path.exists(checkpoint_dir): os.mkdir(checkpoint_dir)

    # Dataset and Dataloader setup
    train_dataset = Dataset('train')
    test_dataset = Dataset('val')

    train_data_loader = data_utils.DataLoader(
        train_dataset, batch_size=hparams.syncnet_batch_size, shuffle=True,
        num_workers=hparams.num_workers)

    test_data_loader = data_utils.DataLoader(
        test_dataset, batch_size=hparams.syncnet_batch_size,
        num_workers=8)

    device = torch.device("cuda" if use_cuda else "cpu")

    # Model
    model = SyncNet().to(device)
    print('total trainable params {}'.format(sum(p.numel() for p in model.parameters() if p.requires_grad)))

    optimizer = optim.Adam([p for p in model.parameters() if p.requires_grad],
                           lr=hparams.syncnet_lr)

    if checkpoint_path is not None:
        load_checkpoint(checkpoint_path, model, optimizer, reset_optimizer=False)

    train(device, model, train_data_loader, test_data_loader, optimizer,
          checkpoint_dir=checkpoint_dir,
          checkpoint_interval=hparams.syncnet_checkpoint_interval,
          nepochs=hparams.nepochs)