File size: 4,142 Bytes
a0bcaae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import matplotlib
from pti.pti_configs import paths_config
matplotlib.use('Agg')
import torch
from torch import nn
from pti.pti_models.e4e.encoders import psp_encoders
from pti.pti_models.e4e.stylegan2.model import Generator


def get_keys(d, name):
    if 'state_dict' in d:
        d = d['state_dict']
    d_filt = {k[len(name) + 1:]: v for k, v in d.items() if k[:len(name)] == name}
    return d_filt


class pSp(nn.Module):

    def __init__(self, opts):
        super(pSp, self).__init__()
        self.opts = opts
        # Define architecture
        self.encoder = self.set_encoder()
        self.decoder = Generator(opts.stylegan_size, 512, 8, channel_multiplier=2)
        self.face_pool = torch.nn.AdaptiveAvgPool2d((256, 256 // 2))
        # Load weights if needed
        self.load_weights()

    def set_encoder(self):
        if self.opts.encoder_type == 'GradualStyleEncoder':
            encoder = psp_encoders.GradualStyleEncoder(50, 'ir_se', self.opts)
        elif self.opts.encoder_type == 'Encoder4Editing':
            encoder = psp_encoders.Encoder4Editing(50, 'ir_se', self.opts)
        elif self.opts.encoder_type == 'SingleStyleCodeEncoder':
            encoder = psp_encoders.BackboneEncoderUsingLastLayerIntoW(50, 'ir_se', self.opts)
        else:
            raise Exception('{} is not a valid encoders'.format(self.opts.encoder_type))
        return encoder

    def load_weights(self):
        if self.opts.checkpoint_path is not None:
            print('Loading e4e over the pSp framework from checkpoint: {}'.format(self.opts.checkpoint_path))
            ckpt = torch.load(self.opts.checkpoint_path, map_location='cpu')
            self.encoder.load_state_dict(get_keys(ckpt, 'encoder'), strict=True)
            self.decoder.load_state_dict(get_keys(ckpt, 'decoder'), strict=True)
            self.__load_latent_avg(ckpt)
        else:
            print('Loading encoders weights from irse50!')
            encoder_ckpt = torch.load(model_paths['ir_se50'])
            self.encoder.load_state_dict(encoder_ckpt, strict=False)
            print('Loading decoder weights from pretrained!')
            ckpt = torch.load(self.opts.stylegan_weights)
            self.decoder.load_state_dict(ckpt['g_ema'], strict=False)
            self.__load_latent_avg(ckpt, repeat=self.encoder.style_count)

    def forward(self, x, resize=True, latent_mask=None, input_code=False, randomize_noise=True,
                inject_latent=None, return_latents=False, alpha=None):
        if input_code:
            codes = x
        else:
            codes = self.encoder(x)
            # normalize with respect to the center of an average face
            if self.opts.start_from_latent_avg:
                if codes.ndim == 2:
                    codes = codes + self.latent_avg.repeat(codes.shape[0], 1, 1)[:, 0, :]
                else:
                    codes = codes + self.latent_avg.repeat(codes.shape[0], 1, 1)

        if latent_mask is not None:
            for i in latent_mask:
                if inject_latent is not None:
                    if alpha is not None:
                        codes[:, i] = alpha * inject_latent[:, i] + (1 - alpha) * codes[:, i]
                    else:
                        codes[:, i] = inject_latent[:, i]
                else:
                    codes[:, i] = 0

        input_is_latent = not input_code
        images, result_latent = self.decoder([codes],
                                             input_is_latent=input_is_latent,
                                             randomize_noise=randomize_noise,
                                             return_latents=return_latents)

        if resize:
            images = self.face_pool(images)

        if return_latents:
            return images, result_latent
        else:
            return images

    def __load_latent_avg(self, ckpt, repeat=None):
        if 'latent_avg' in ckpt:
            self.latent_avg = ckpt['latent_avg'].to(self.opts.device)
            if repeat is not None:
                self.latent_avg = self.latent_avg.repeat(repeat, 1)
        else:
            self.latent_avg = None