Upload 6 files

audio.py

@@ -0,0 +1,136 @@
+import librosa
+import librosa.filters
+import numpy as np
+# import tensorflow as tf
+from scipy import signal
+from scipy.io import wavfile
+from hparams import hparams as hp
+
+def load_wav(path, sr):
+    return librosa.core.load(path, sr=sr)[0]
+
+def save_wav(wav, path, sr):
+    wav *= 32767 / max(0.01, np.max(np.abs(wav)))
+    #proposed by @dsmiller
+    wavfile.write(path, sr, wav.astype(np.int16))
+
+def save_wavenet_wav(wav, path, sr):
+    librosa.output.write_wav(path, wav, sr=sr)
+
+def preemphasis(wav, k, preemphasize=True):
+    if preemphasize:
+        return signal.lfilter([1, -k], [1], wav)
+    return wav
+
+def inv_preemphasis(wav, k, inv_preemphasize=True):
+    if inv_preemphasize:
+        return signal.lfilter([1], [1, -k], wav)
+    return wav
+
+def get_hop_size():
+    hop_size = hp.hop_size
+    if hop_size is None:
+        assert hp.frame_shift_ms is not None
+        hop_size = int(hp.frame_shift_ms / 1000 * hp.sample_rate)
+    return hop_size
+
+def linearspectrogram(wav):
+    D = _stft(preemphasis(wav, hp.preemphasis, hp.preemphasize))
+    S = _amp_to_db(np.abs(D)) - hp.ref_level_db
+    
+    if hp.signal_normalization:
+        return _normalize(S)
+    return S
+
+def melspectrogram(wav):
+    D = _stft(preemphasis(wav, hp.preemphasis, hp.preemphasize))
+    S = _amp_to_db(_linear_to_mel(np.abs(D))) - hp.ref_level_db
+    
+    if hp.signal_normalization:
+        return _normalize(S)
+    return S
+
+def _lws_processor():
+    import lws
+    return lws.lws(hp.n_fft, get_hop_size(), fftsize=hp.win_size, mode="speech")
+
+def _stft(y):
+    if hp.use_lws:
+        return _lws_processor(hp).stft(y).T
+    else:
+        return librosa.stft(y=y, n_fft=hp.n_fft, hop_length=get_hop_size(), win_length=hp.win_size)
+
+##########################################################
+#Those are only correct when using lws!!! (This was messing with Wavenet quality for a long time!)
+def num_frames(length, fsize, fshift):
+    """Compute number of time frames of spectrogram
+    """
+    pad = (fsize - fshift)
+    if length % fshift == 0:
+        M = (length + pad * 2 - fsize) // fshift + 1
+    else:
+        M = (length + pad * 2 - fsize) // fshift + 2
+    return M
+
+
+def pad_lr(x, fsize, fshift):
+    """Compute left and right padding
+    """
+    M = num_frames(len(x), fsize, fshift)
+    pad = (fsize - fshift)
+    T = len(x) + 2 * pad
+    r = (M - 1) * fshift + fsize - T
+    return pad, pad + r
+##########################################################
+#Librosa correct padding
+def librosa_pad_lr(x, fsize, fshift):
+    return 0, (x.shape[0] // fshift + 1) * fshift - x.shape[0]
+
+# Conversions
+_mel_basis = None
+
+def _linear_to_mel(spectogram):
+    global _mel_basis
+    if _mel_basis is None:
+        _mel_basis = _build_mel_basis()
+    return np.dot(_mel_basis, spectogram)
+
+def _build_mel_basis():
+    assert hp.fmax <= hp.sample_rate // 2
+    return librosa.filters.mel(hp.sample_rate, hp.n_fft, n_mels=hp.num_mels,
+                               fmin=hp.fmin, fmax=hp.fmax)
+
+def _amp_to_db(x):
+    min_level = np.exp(hp.min_level_db / 20 * np.log(10))
+    return 20 * np.log10(np.maximum(min_level, x))
+
+def _db_to_amp(x):
+    return np.power(10.0, (x) * 0.05)
+
+def _normalize(S):
+    if hp.allow_clipping_in_normalization:
+        if hp.symmetric_mels:
+            return np.clip((2 * hp.max_abs_value) * ((S - hp.min_level_db) / (-hp.min_level_db)) - hp.max_abs_value,
+                           -hp.max_abs_value, hp.max_abs_value)
+        else:
+            return np.clip(hp.max_abs_value * ((S - hp.min_level_db) / (-hp.min_level_db)), 0, hp.max_abs_value)
+    
+    assert S.max() <= 0 and S.min() - hp.min_level_db >= 0
+    if hp.symmetric_mels:
+        return (2 * hp.max_abs_value) * ((S - hp.min_level_db) / (-hp.min_level_db)) - hp.max_abs_value
+    else:
+        return hp.max_abs_value * ((S - hp.min_level_db) / (-hp.min_level_db))
+
+def _denormalize(D):
+    if hp.allow_clipping_in_normalization:
+        if hp.symmetric_mels:
+            return (((np.clip(D, -hp.max_abs_value,
+                              hp.max_abs_value) + hp.max_abs_value) * -hp.min_level_db / (2 * hp.max_abs_value))
+                    + hp.min_level_db)
+        else:
+            return ((np.clip(D, 0, hp.max_abs_value) * -hp.min_level_db / hp.max_abs_value) + hp.min_level_db)
+    
+    if hp.symmetric_mels:
+        return (((D + hp.max_abs_value) * -hp.min_level_db / (2 * hp.max_abs_value)) + hp.min_level_db)
+    else:
+        return ((D * -hp.min_level_db / hp.max_abs_value) + hp.min_level_db)

color_syncnet_train.py

@@ -0,0 +1,279 @@
+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)

hparams.py

@@ -0,0 +1,101 @@
+from glob import glob
+import os
+
+def get_image_list(data_root, split):
+	filelist = []
+
+	with open('filelists/{}.txt'.format(split)) as f:
+		for line in f:
+			line = line.strip()
+			if ' ' in line: line = line.split()[0]
+			filelist.append(os.path.join(data_root, line))
+
+	return filelist
+
+class HParams:
+	def __init__(self, **kwargs):
+		self.data = {}
+
+		for key, value in kwargs.items():
+			self.data[key] = value
+
+	def __getattr__(self, key):
+		if key not in self.data:
+			raise AttributeError("'HParams' object has no attribute %s" % key)
+		return self.data[key]
+
+	def set_hparam(self, key, value):
+		self.data[key] = value
+
+
+# Default hyperparameters
+hparams = HParams(
+	num_mels=80,  # Number of mel-spectrogram channels and local conditioning dimensionality
+	#  network
+	rescale=True,  # Whether to rescale audio prior to preprocessing
+	rescaling_max=0.9,  # Rescaling value
+	
+	# Use LWS (https://github.com/Jonathan-LeRoux/lws) for STFT and phase reconstruction
+	# It"s preferred to set True to use with https://github.com/r9y9/wavenet_vocoder
+	# Does not work if n_ffit is not multiple of hop_size!!
+	use_lws=False,
+	
+	n_fft=800,  # Extra window size is filled with 0 paddings to match this parameter
+	hop_size=200,  # For 16000Hz, 200 = 12.5 ms (0.0125 * sample_rate)
+	win_size=800,  # For 16000Hz, 800 = 50 ms (If None, win_size = n_fft) (0.05 * sample_rate)
+	sample_rate=16000,  # 16000Hz (corresponding to librispeech) (sox --i <filename>)
+	
+	frame_shift_ms=None,  # Can replace hop_size parameter. (Recommended: 12.5)
+	
+	# Mel and Linear spectrograms normalization/scaling and clipping
+	signal_normalization=True,
+	# Whether to normalize mel spectrograms to some predefined range (following below parameters)
+	allow_clipping_in_normalization=True,  # Only relevant if mel_normalization = True
+	symmetric_mels=True,
+	# Whether to scale the data to be symmetric around 0. (Also multiplies the output range by 2, 
+	# faster and cleaner convergence)
+	max_abs_value=4.,
+	# max absolute value of data. If symmetric, data will be [-max, max] else [0, max] (Must not 
+	# be too big to avoid gradient explosion, 
+	# not too small for fast convergence)
+	# Contribution by @begeekmyfriend
+	# Spectrogram Pre-Emphasis (Lfilter: Reduce spectrogram noise and helps model certitude 
+	# levels. Also allows for better G&L phase reconstruction)
+	preemphasize=True,  # whether to apply filter
+	preemphasis=0.97,  # filter coefficient.
+	
+	# Limits
+	min_level_db=-100,
+	ref_level_db=20,
+	fmin=55,
+	# Set this to 55 if your speaker is male! if female, 95 should help taking off noise. (To 
+	# test depending on dataset. Pitch info: male~[65, 260], female~[100, 525])
+	fmax=7600,  # To be increased/reduced depending on data.
+
+	###################### Our training parameters #################################
+	img_size=96,
+	fps=25,
+	
+	batch_size=16,
+	initial_learning_rate=1e-4,
+	nepochs=200000000000000000,  ### ctrl + c, stop whenever eval loss is consistently greater than train loss for ~10 epochs
+	num_workers=16,
+	checkpoint_interval=3000,
+	eval_interval=3000,
+    save_optimizer_state=True,
+
+    syncnet_wt=0.0, # is initially zero, will be set automatically to 0.03 later. Leads to faster convergence. 
+	syncnet_batch_size=64,
+	syncnet_lr=1e-4,
+	syncnet_eval_interval=10000,
+	syncnet_checkpoint_interval=10000,
+
+	disc_wt=0.07,
+	disc_initial_learning_rate=1e-4,
+)
+
+
+def hparams_debug_string():
+	values = hparams.values()
+	hp = ["  %s: %s" % (name, values[name]) for name in sorted(values) if name != "sentences"]
+	return "Hyperparameters:\n" + "\n".join(hp)

hq_wav2lip_train.py

@@ -0,0 +1,443 @@
+from os.path import dirname, join, basename, isfile
+from tqdm import tqdm
+
+from models import SyncNet_color as SyncNet
+from models import Wav2Lip, Wav2Lip_disc_qual
+import audio
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+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 Wav2Lip model WITH the visual quality discriminator')
+
+parser.add_argument("--data_root", help="Root folder of the preprocessed LRS2 dataset", required=True, type=str)
+
+parser.add_argument('--checkpoint_dir', help='Save checkpoints to this directory', required=True, type=str)
+parser.add_argument('--syncnet_checkpoint_path', help='Load the pre-trained Expert discriminator', required=True, type=str)
+
+parser.add_argument('--checkpoint_path', help='Resume generator from this checkpoint', default=None, type=str)
+parser.add_argument('--disc_checkpoint_path', help='Resume quality disc 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 read_window(self, window_fnames):
+        if window_fnames is None: return None
+        window = []
+        for fname in window_fnames:
+            img = cv2.imread(fname)
+            if img is None:
+                return None
+            try:
+                img = cv2.resize(img, (hparams.img_size, hparams.img_size))
+            except Exception as e:
+                return None
+
+            window.append(img)
+
+        return window
+
+    def crop_audio_window(self, spec, start_frame):
+        if type(start_frame) == int:
+            start_frame_num = start_frame
+        else:
+            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 get_segmented_mels(self, spec, start_frame):
+        mels = []
+        assert syncnet_T == 5
+        start_frame_num = self.get_frame_id(start_frame) + 1 # 0-indexing ---> 1-indexing
+        if start_frame_num - 2 < 0: return None
+        for i in range(start_frame_num, start_frame_num + syncnet_T):
+            m = self.crop_audio_window(spec, i - 2)
+            if m.shape[0] != syncnet_mel_step_size:
+                return None
+            mels.append(m.T)
+
+        mels = np.asarray(mels)
+
+        return mels
+
+    def prepare_window(self, window):
+        # 3 x T x H x W
+        x = np.asarray(window) / 255.
+        x = np.transpose(x, (3, 0, 1, 2))
+
+        return x
+
+    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)
+
+            window_fnames = self.get_window(img_name)
+            wrong_window_fnames = self.get_window(wrong_img_name)
+            if window_fnames is None or wrong_window_fnames is None:
+                continue
+
+            window = self.read_window(window_fnames)
+            if window is None:
+                continue
+
+            wrong_window = self.read_window(wrong_window_fnames)
+            if wrong_window is None:
+                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
+
+            indiv_mels = self.get_segmented_mels(orig_mel.copy(), img_name)
+            if indiv_mels is None: continue
+
+            window = self.prepare_window(window)
+            y = window.copy()
+            window[:, :, window.shape[2]//2:] = 0.
+
+            wrong_window = self.prepare_window(wrong_window)
+            x = np.concatenate([window, wrong_window], axis=0)
+
+            x = torch.FloatTensor(x)
+            mel = torch.FloatTensor(mel.T).unsqueeze(0)
+            indiv_mels = torch.FloatTensor(indiv_mels).unsqueeze(1)
+            y = torch.FloatTensor(y)
+            return x, indiv_mels, mel, y
+
+def save_sample_images(x, g, gt, global_step, checkpoint_dir):
+    x = (x.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+    g = (g.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+    gt = (gt.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+
+    refs, inps = x[..., 3:], x[..., :3]
+    folder = join(checkpoint_dir, "samples_step{:09d}".format(global_step))
+    if not os.path.exists(folder): os.mkdir(folder)
+    collage = np.concatenate((refs, inps, g, gt), axis=-2)
+    for batch_idx, c in enumerate(collage):
+        for t in range(len(c)):
+            cv2.imwrite('{}/{}_{}.jpg'.format(folder, batch_idx, t), c[t])
+
+logloss = nn.BCELoss()
+def cosine_loss(a, v, y):
+    d = nn.functional.cosine_similarity(a, v)
+    loss = logloss(d.unsqueeze(1), y)
+
+    return loss
+
+device = torch.device("cuda" if use_cuda else "cpu")
+syncnet = SyncNet().to(device)
+for p in syncnet.parameters():
+    p.requires_grad = False
+
+recon_loss = nn.L1Loss()
+def get_sync_loss(mel, g):
+    g = g[:, :, :, g.size(3)//2:]
+    g = torch.cat([g[:, :, i] for i in range(syncnet_T)], dim=1)
+    # B, 3 * T, H//2, W
+    a, v = syncnet(mel, g)
+    y = torch.ones(g.size(0), 1).float().to(device)
+    return cosine_loss(a, v, y)
+
+def train(device, model, disc, train_data_loader, test_data_loader, optimizer, disc_optimizer,
+          checkpoint_dir=None, checkpoint_interval=None, nepochs=None):
+    global global_step, global_epoch
+    resumed_step = global_step
+
+    while global_epoch < nepochs:
+        print('Starting Epoch: {}'.format(global_epoch))
+        running_sync_loss, running_l1_loss, disc_loss, running_perceptual_loss = 0., 0., 0., 0.
+        running_disc_real_loss, running_disc_fake_loss = 0., 0.
+        prog_bar = tqdm(enumerate(train_data_loader))
+        for step, (x, indiv_mels, mel, gt) in prog_bar:
+            disc.train()
+            model.train()
+
+            x = x.to(device)
+            mel = mel.to(device)
+            indiv_mels = indiv_mels.to(device)
+            gt = gt.to(device)
+
+            ### Train generator now. Remove ALL grads. 
+            optimizer.zero_grad()
+            disc_optimizer.zero_grad()
+
+            g = model(indiv_mels, x)
+
+            if hparams.syncnet_wt > 0.:
+                sync_loss = get_sync_loss(mel, g)
+            else:
+                sync_loss = 0.
+
+            if hparams.disc_wt > 0.:
+                perceptual_loss = disc.perceptual_forward(g)
+            else:
+                perceptual_loss = 0.
+
+            l1loss = recon_loss(g, gt)
+
+            loss = hparams.syncnet_wt * sync_loss + hparams.disc_wt * perceptual_loss + \
+                                    (1. - hparams.syncnet_wt - hparams.disc_wt) * l1loss
+
+            loss.backward()
+            optimizer.step()
+
+            ### Remove all gradients before Training disc
+            disc_optimizer.zero_grad()
+
+            pred = disc(gt)
+            disc_real_loss = F.binary_cross_entropy(pred, torch.ones((len(pred), 1)).to(device))
+            disc_real_loss.backward()
+
+            pred = disc(g.detach())
+            disc_fake_loss = F.binary_cross_entropy(pred, torch.zeros((len(pred), 1)).to(device))
+            disc_fake_loss.backward()
+
+            disc_optimizer.step()
+
+            running_disc_real_loss += disc_real_loss.item()
+            running_disc_fake_loss += disc_fake_loss.item()
+
+            if global_step % checkpoint_interval == 0:
+                save_sample_images(x, g, gt, global_step, checkpoint_dir)
+
+            # Logs
+            global_step += 1
+            cur_session_steps = global_step - resumed_step
+
+            running_l1_loss += l1loss.item()
+            if hparams.syncnet_wt > 0.:
+                running_sync_loss += sync_loss.item()
+            else:
+                running_sync_loss += 0.
+
+            if hparams.disc_wt > 0.:
+                running_perceptual_loss += perceptual_loss.item()
+            else:
+                running_perceptual_loss += 0.
+
+            if global_step == 1 or global_step % checkpoint_interval == 0:
+                save_checkpoint(
+                    model, optimizer, global_step, checkpoint_dir, global_epoch)
+                save_checkpoint(disc, disc_optimizer, global_step, checkpoint_dir, global_epoch, prefix='disc_')
+
+
+            if global_step % hparams.eval_interval == 0:
+                with torch.no_grad():
+                    average_sync_loss = eval_model(test_data_loader, global_step, device, model, disc)
+
+                    if average_sync_loss < .75:
+                        hparams.set_hparam('syncnet_wt', 0.03)
+
+            prog_bar.set_description('L1: {}, Sync: {}, Percep: {} | Fake: {}, Real: {}'.format(running_l1_loss / (step + 1),
+                                                                                        running_sync_loss / (step + 1),
+                                                                                        running_perceptual_loss / (step + 1),
+                                                                                        running_disc_fake_loss / (step + 1),
+                                                                                        running_disc_real_loss / (step + 1)))
+
+        global_epoch += 1
+
+def eval_model(test_data_loader, global_step, device, model, disc):
+    eval_steps = 300
+    print('Evaluating for {} steps'.format(eval_steps))
+    running_sync_loss, running_l1_loss, running_disc_real_loss, running_disc_fake_loss, running_perceptual_loss = [], [], [], [], []
+    while 1:
+        for step, (x, indiv_mels, mel, gt) in enumerate((test_data_loader)):
+            model.eval()
+            disc.eval()
+
+            x = x.to(device)
+            mel = mel.to(device)
+            indiv_mels = indiv_mels.to(device)
+            gt = gt.to(device)
+
+            pred = disc(gt)
+            disc_real_loss = F.binary_cross_entropy(pred, torch.ones((len(pred), 1)).to(device))
+
+            g = model(indiv_mels, x)
+            pred = disc(g)
+            disc_fake_loss = F.binary_cross_entropy(pred, torch.zeros((len(pred), 1)).to(device))
+
+            running_disc_real_loss.append(disc_real_loss.item())
+            running_disc_fake_loss.append(disc_fake_loss.item())
+
+            sync_loss = get_sync_loss(mel, g)
+            
+            if hparams.disc_wt > 0.:
+                perceptual_loss = disc.perceptual_forward(g)
+            else:
+                perceptual_loss = 0.
+
+            l1loss = recon_loss(g, gt)
+
+            loss = hparams.syncnet_wt * sync_loss + hparams.disc_wt * perceptual_loss + \
+                                    (1. - hparams.syncnet_wt - hparams.disc_wt) * l1loss
+
+            running_l1_loss.append(l1loss.item())
+            running_sync_loss.append(sync_loss.item())
+            
+            if hparams.disc_wt > 0.:
+                running_perceptual_loss.append(perceptual_loss.item())
+            else:
+                running_perceptual_loss.append(0.)
+
+            if step > eval_steps: break
+
+        print('L1: {}, Sync: {}, Percep: {} | Fake: {}, Real: {}'.format(sum(running_l1_loss) / len(running_l1_loss),
+                                                            sum(running_sync_loss) / len(running_sync_loss),
+                                                            sum(running_perceptual_loss) / len(running_perceptual_loss),
+                                                            sum(running_disc_fake_loss) / len(running_disc_fake_loss),
+                                                             sum(running_disc_real_loss) / len(running_disc_real_loss)))
+        return sum(running_sync_loss) / len(running_sync_loss)
+
+
+def save_checkpoint(model, optimizer, step, checkpoint_dir, epoch, prefix=''):
+    checkpoint_path = join(
+        checkpoint_dir, "{}checkpoint_step{:09d}.pth".format(prefix, 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, overwrite_global_states=True):
+    global global_step
+    global global_epoch
+
+    print("Load checkpoint from: {}".format(path))
+    checkpoint = _load(path)
+    s = checkpoint["state_dict"]
+    new_s = {}
+    for k, v in s.items():
+        new_s[k.replace('module.', '')] = v
+    model.load_state_dict(new_s)
+    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"])
+    if overwrite_global_states:
+        global_step = checkpoint["global_step"]
+        global_epoch = checkpoint["global_epoch"]
+
+    return model
+
+if __name__ == "__main__":
+    checkpoint_dir = args.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.batch_size, shuffle=True,
+        num_workers=hparams.num_workers)
+
+    test_data_loader = data_utils.DataLoader(
+        test_dataset, batch_size=hparams.batch_size,
+        num_workers=4)
+
+    device = torch.device("cuda" if use_cuda else "cpu")
+
+     # Model
+    model = Wav2Lip().to(device)
+    disc = Wav2Lip_disc_qual().to(device)
+
+    print('total trainable params {}'.format(sum(p.numel() for p in model.parameters() if p.requires_grad)))
+    print('total DISC trainable params {}'.format(sum(p.numel() for p in disc.parameters() if p.requires_grad)))
+
+    optimizer = optim.Adam([p for p in model.parameters() if p.requires_grad],
+                           lr=hparams.initial_learning_rate, betas=(0.5, 0.999))
+    disc_optimizer = optim.Adam([p for p in disc.parameters() if p.requires_grad],
+                           lr=hparams.disc_initial_learning_rate, betas=(0.5, 0.999))
+
+    if args.checkpoint_path is not None:
+        load_checkpoint(args.checkpoint_path, model, optimizer, reset_optimizer=False)
+
+    if args.disc_checkpoint_path is not None:
+        load_checkpoint(args.disc_checkpoint_path, disc, disc_optimizer, 
+                                reset_optimizer=False, overwrite_global_states=False)
+        
+    load_checkpoint(args.syncnet_checkpoint_path, syncnet, None, reset_optimizer=True, 
+                                overwrite_global_states=False)
+
+    if not os.path.exists(checkpoint_dir):
+        os.mkdir(checkpoint_dir)
+
+    # Train!
+    train(device, model, disc, train_data_loader, test_data_loader, optimizer, disc_optimizer,
+              checkpoint_dir=checkpoint_dir,
+              checkpoint_interval=hparams.checkpoint_interval,
+              nepochs=hparams.nepochs)

preprocess.py

@@ -0,0 +1,113 @@
+import sys
+
+if sys.version_info[0] < 3 and sys.version_info[1] < 2:
+	raise Exception("Must be using >= Python 3.2")
+
+from os import listdir, path
+
+if not path.isfile('face_detection/detection/sfd/s3fd.pth'):
+	raise FileNotFoundError('Save the s3fd model to face_detection/detection/sfd/s3fd.pth \
+							before running this script!')
+
+import multiprocessing as mp
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import numpy as np
+import argparse, os, cv2, traceback, subprocess
+from tqdm import tqdm
+from glob import glob
+import audio
+from hparams import hparams as hp
+
+import face_detection
+
+parser = argparse.ArgumentParser()
+
+parser.add_argument('--ngpu', help='Number of GPUs across which to run in parallel', default=1, type=int)
+parser.add_argument('--batch_size', help='Single GPU Face detection batch size', default=32, type=int)
+parser.add_argument("--data_root", help="Root folder of the LRS2 dataset", required=True)
+parser.add_argument("--preprocessed_root", help="Root folder of the preprocessed dataset", required=True)
+
+args = parser.parse_args()
+
+fa = [face_detection.FaceAlignment(face_detection.LandmarksType._2D, flip_input=False, 
+									device='cuda:{}'.format(id)) for id in range(args.ngpu)]
+
+template = 'ffmpeg -loglevel panic -y -i {} -strict -2 {}'
+# template2 = 'ffmpeg -hide_banner -loglevel panic -threads 1 -y -i {} -async 1 -ac 1 -vn -acodec pcm_s16le -ar 16000 {}'
+
+def process_video_file(vfile, args, gpu_id):
+	video_stream = cv2.VideoCapture(vfile)
+	
+	frames = []
+	while 1:
+		still_reading, frame = video_stream.read()
+		if not still_reading:
+			video_stream.release()
+			break
+		frames.append(frame)
+	
+	vidname = os.path.basename(vfile).split('.')[0]
+	dirname = vfile.split('/')[-2]
+
+	fulldir = path.join(args.preprocessed_root, dirname, vidname)
+	os.makedirs(fulldir, exist_ok=True)
+
+	batches = [frames[i:i + args.batch_size] for i in range(0, len(frames), args.batch_size)]
+
+	i = -1
+	for fb in batches:
+		preds = fa[gpu_id].get_detections_for_batch(np.asarray(fb))
+
+		for j, f in enumerate(preds):
+			i += 1
+			if f is None:
+				continue
+
+			x1, y1, x2, y2 = f
+			cv2.imwrite(path.join(fulldir, '{}.jpg'.format(i)), fb[j][y1:y2, x1:x2])
+
+def process_audio_file(vfile, args):
+	vidname = os.path.basename(vfile).split('.')[0]
+	dirname = vfile.split('/')[-2]
+
+	fulldir = path.join(args.preprocessed_root, dirname, vidname)
+	os.makedirs(fulldir, exist_ok=True)
+
+	wavpath = path.join(fulldir, 'audio.wav')
+
+	command = template.format(vfile, wavpath)
+	subprocess.call(command, shell=True)
+
+	
+def mp_handler(job):
+	vfile, args, gpu_id = job
+	try:
+		process_video_file(vfile, args, gpu_id)
+	except KeyboardInterrupt:
+		exit(0)
+	except:
+		traceback.print_exc()
+		
+def main(args):
+	print('Started processing for {} with {} GPUs'.format(args.data_root, args.ngpu))
+
+	filelist = glob(path.join(args.data_root, '*/*.mp4'))
+
+	jobs = [(vfile, args, i%args.ngpu) for i, vfile in enumerate(filelist)]
+	p = ThreadPoolExecutor(args.ngpu)
+	futures = [p.submit(mp_handler, j) for j in jobs]
+	_ = [r.result() for r in tqdm(as_completed(futures), total=len(futures))]
+
+	print('Dumping audios...')
+
+	for vfile in tqdm(filelist):
+		try:
+			process_audio_file(vfile, args)
+		except KeyboardInterrupt:
+			exit(0)
+		except:
+			traceback.print_exc()
+			continue
+
+if __name__ == '__main__':
+	main(args)

wav2lip_train.py

@@ -0,0 +1,374 @@
+from os.path import dirname, join, basename, isfile
+from tqdm import tqdm
+
+from models import SyncNet_color as SyncNet
+from models import Wav2Lip as Wav2Lip
+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 Wav2Lip model without the visual quality discriminator')
+
+parser.add_argument("--data_root", help="Root folder of the preprocessed LRS2 dataset", required=True, type=str)
+
+parser.add_argument('--checkpoint_dir', help='Save checkpoints to this directory', required=True, type=str)
+parser.add_argument('--syncnet_checkpoint_path', help='Load the pre-trained Expert discriminator', required=True, type=str)
+
+parser.add_argument('--checkpoint_path', help='Resume 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 read_window(self, window_fnames):
+        if window_fnames is None: return None
+        window = []
+        for fname in window_fnames:
+            img = cv2.imread(fname)
+            if img is None:
+                return None
+            try:
+                img = cv2.resize(img, (hparams.img_size, hparams.img_size))
+            except Exception as e:
+                return None
+
+            window.append(img)
+
+        return window
+
+    def crop_audio_window(self, spec, start_frame):
+        if type(start_frame) == int:
+            start_frame_num = start_frame
+        else:
+            start_frame_num = self.get_frame_id(start_frame) # 0-indexing ---> 1-indexing
+        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 get_segmented_mels(self, spec, start_frame):
+        mels = []
+        assert syncnet_T == 5
+        start_frame_num = self.get_frame_id(start_frame) + 1 # 0-indexing ---> 1-indexing
+        if start_frame_num - 2 < 0: return None
+        for i in range(start_frame_num, start_frame_num + syncnet_T):
+            m = self.crop_audio_window(spec, i - 2)
+            if m.shape[0] != syncnet_mel_step_size:
+                return None
+            mels.append(m.T)
+
+        mels = np.asarray(mels)
+
+        return mels
+
+    def prepare_window(self, window):
+        # 3 x T x H x W
+        x = np.asarray(window) / 255.
+        x = np.transpose(x, (3, 0, 1, 2))
+
+        return x
+
+    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)
+
+            window_fnames = self.get_window(img_name)
+            wrong_window_fnames = self.get_window(wrong_img_name)
+            if window_fnames is None or wrong_window_fnames is None:
+                continue
+
+            window = self.read_window(window_fnames)
+            if window is None:
+                continue
+
+            wrong_window = self.read_window(wrong_window_fnames)
+            if wrong_window is None:
+                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
+
+            indiv_mels = self.get_segmented_mels(orig_mel.copy(), img_name)
+            if indiv_mels is None: continue
+
+            window = self.prepare_window(window)
+            y = window.copy()
+            window[:, :, window.shape[2]//2:] = 0.
+
+            wrong_window = self.prepare_window(wrong_window)
+            x = np.concatenate([window, wrong_window], axis=0)
+
+            x = torch.FloatTensor(x)
+            mel = torch.FloatTensor(mel.T).unsqueeze(0)
+            indiv_mels = torch.FloatTensor(indiv_mels).unsqueeze(1)
+            y = torch.FloatTensor(y)
+            return x, indiv_mels, mel, y
+
+def save_sample_images(x, g, gt, global_step, checkpoint_dir):
+    x = (x.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+    g = (g.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+    gt = (gt.detach().cpu().numpy().transpose(0, 2, 3, 4, 1) * 255.).astype(np.uint8)
+
+    refs, inps = x[..., 3:], x[..., :3]
+    folder = join(checkpoint_dir, "samples_step{:09d}".format(global_step))
+    if not os.path.exists(folder): os.mkdir(folder)
+    collage = np.concatenate((refs, inps, g, gt), axis=-2)
+    for batch_idx, c in enumerate(collage):
+        for t in range(len(c)):
+            cv2.imwrite('{}/{}_{}.jpg'.format(folder, batch_idx, t), c[t])
+
+logloss = nn.BCELoss()
+def cosine_loss(a, v, y):
+    d = nn.functional.cosine_similarity(a, v)
+    loss = logloss(d.unsqueeze(1), y)
+
+    return loss
+
+device = torch.device("cuda" if use_cuda else "cpu")
+syncnet = SyncNet().to(device)
+for p in syncnet.parameters():
+    p.requires_grad = False
+
+recon_loss = nn.L1Loss()
+def get_sync_loss(mel, g):
+    g = g[:, :, :, g.size(3)//2:]
+    g = torch.cat([g[:, :, i] for i in range(syncnet_T)], dim=1)
+    # B, 3 * T, H//2, W
+    a, v = syncnet(mel, g)
+    y = torch.ones(g.size(0), 1).float().to(device)
+    return cosine_loss(a, v, y)
+
+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:
+        print('Starting Epoch: {}'.format(global_epoch))
+        running_sync_loss, running_l1_loss = 0., 0.
+        prog_bar = tqdm(enumerate(train_data_loader))
+        for step, (x, indiv_mels, mel, gt) in prog_bar:
+            model.train()
+            optimizer.zero_grad()
+
+            # Move data to CUDA device
+            x = x.to(device)
+            mel = mel.to(device)
+            indiv_mels = indiv_mels.to(device)
+            gt = gt.to(device)
+
+            g = model(indiv_mels, x)
+
+            if hparams.syncnet_wt > 0.:
+                sync_loss = get_sync_loss(mel, g)
+            else:
+                sync_loss = 0.
+
+            l1loss = recon_loss(g, gt)
+
+            loss = hparams.syncnet_wt * sync_loss + (1 - hparams.syncnet_wt) * l1loss
+            loss.backward()
+            optimizer.step()
+
+            if global_step % checkpoint_interval == 0:
+                save_sample_images(x, g, gt, global_step, checkpoint_dir)
+
+            global_step += 1
+            cur_session_steps = global_step - resumed_step
+
+            running_l1_loss += l1loss.item()
+            if hparams.syncnet_wt > 0.:
+                running_sync_loss += sync_loss.item()
+            else:
+                running_sync_loss += 0.
+
+            if global_step == 1 or global_step % checkpoint_interval == 0:
+                save_checkpoint(
+                    model, optimizer, global_step, checkpoint_dir, global_epoch)
+
+            if global_step == 1 or global_step % hparams.eval_interval == 0:
+                with torch.no_grad():
+                    average_sync_loss = eval_model(test_data_loader, global_step, device, model, checkpoint_dir)
+
+                    if average_sync_loss < .75:
+                        hparams.set_hparam('syncnet_wt', 0.01) # without image GAN a lesser weight is sufficient
+
+            prog_bar.set_description('L1: {}, Sync Loss: {}'.format(running_l1_loss / (step + 1),
+                                                                    running_sync_loss / (step + 1)))
+
+        global_epoch += 1
+        
+
+def eval_model(test_data_loader, global_step, device, model, checkpoint_dir):
+    eval_steps = 700
+    print('Evaluating for {} steps'.format(eval_steps))
+    sync_losses, recon_losses = [], []
+    step = 0
+    while 1:
+        for x, indiv_mels, mel, gt in test_data_loader:
+            step += 1
+            model.eval()
+
+            # Move data to CUDA device
+            x = x.to(device)
+            gt = gt.to(device)
+            indiv_mels = indiv_mels.to(device)
+            mel = mel.to(device)
+
+            g = model(indiv_mels, x)
+
+            sync_loss = get_sync_loss(mel, g)
+            l1loss = recon_loss(g, gt)
+
+            sync_losses.append(sync_loss.item())
+            recon_losses.append(l1loss.item())
+
+            if step > eval_steps: 
+                averaged_sync_loss = sum(sync_losses) / len(sync_losses)
+                averaged_recon_loss = sum(recon_losses) / len(recon_losses)
+
+                print('L1: {}, Sync loss: {}'.format(averaged_recon_loss, averaged_sync_loss))
+
+                return averaged_sync_loss
+
+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, overwrite_global_states=True):
+    global global_step
+    global global_epoch
+
+    print("Load checkpoint from: {}".format(path))
+    checkpoint = _load(path)
+    s = checkpoint["state_dict"]
+    new_s = {}
+    for k, v in s.items():
+        new_s[k.replace('module.', '')] = v
+    model.load_state_dict(new_s)
+    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"])
+    if overwrite_global_states:
+        global_step = checkpoint["global_step"]
+        global_epoch = checkpoint["global_epoch"]
+
+    return model
+
+if __name__ == "__main__":
+    checkpoint_dir = args.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.batch_size, shuffle=True,
+        num_workers=hparams.num_workers)
+
+    test_data_loader = data_utils.DataLoader(
+        test_dataset, batch_size=hparams.batch_size,
+        num_workers=4)
+
+    device = torch.device("cuda" if use_cuda else "cpu")
+
+    # Model
+    model = Wav2Lip().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.initial_learning_rate)
+
+    if args.checkpoint_path is not None:
+        load_checkpoint(args.checkpoint_path, model, optimizer, reset_optimizer=False)
+        
+    load_checkpoint(args.syncnet_checkpoint_path, syncnet, None, reset_optimizer=True, overwrite_global_states=False)
+
+    if not os.path.exists(checkpoint_dir):
+        os.mkdir(checkpoint_dir)
+
+    # Train!
+    train(device, model, train_data_loader, test_data_loader, optimizer,
+              checkpoint_dir=checkpoint_dir,
+              checkpoint_interval=hparams.checkpoint_interval,
+              nepochs=hparams.nepochs)