File size: 4,307 Bytes
b85284b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from __future__ import annotations

import os
import pathlib
import sys
import zipfile

import huggingface_hub
import numpy as np
import PIL.Image
import torch

sys.path.insert(0, 'Text2Human')

from models.sample_model import SampleFromPoseModel
from utils.language_utils import (generate_shape_attributes,
                                  generate_texture_attributes)
from utils.options import dict_to_nonedict, parse
from utils.util import set_random_seed

COLOR_LIST = [
    (0, 0, 0),
    (255, 250, 250),
    (220, 220, 220),
    (250, 235, 215),
    (255, 250, 205),
    (211, 211, 211),
    (70, 130, 180),
    (127, 255, 212),
    (0, 100, 0),
    (50, 205, 50),
    (255, 255, 0),
    (245, 222, 179),
    (255, 140, 0),
    (255, 0, 0),
    (16, 78, 139),
    (144, 238, 144),
    (50, 205, 174),
    (50, 155, 250),
    (160, 140, 88),
    (213, 140, 88),
    (90, 140, 90),
    (185, 210, 205),
    (130, 165, 180),
    (225, 141, 151),
]


class Model:
    def __init__(self, device: str):
        self.config = self._load_config()
        self.config['device'] = device
        self._download_models()
        self.model = SampleFromPoseModel(self.config)

    def _load_config(self) -> dict:
        path = 'Text2Human/configs/sample_from_pose.yml'
        config = parse(path, is_train=False)
        config = dict_to_nonedict(config)
        return config

    def _download_models(self) -> None:
        model_dir = pathlib.Path('pretrained_models')
        if model_dir.exists():
            return
        token = os.getenv('HF_TOKEN')
        path = huggingface_hub.hf_hub_download('hysts/Text2Human',
                                               'orig/pretrained_models.zip',
                                               use_auth_token=token)
        model_dir.mkdir()
        with zipfile.ZipFile(path) as f:
            f.extractall(model_dir)

    @staticmethod
    def preprocess_pose_image(image: PIL.Image.Image) -> torch.Tensor:
        image = np.array(
            image.resize(
                size=(256, 512),
                resample=PIL.Image.Resampling.LANCZOS))[:, :, 2:].transpose(
                    2, 0, 1).astype(np.float32)
        image = image / 12. - 1
        data = torch.from_numpy(image).unsqueeze(1)
        return data

    @staticmethod
    def process_mask(mask: torch.Tensor) -> torch.Tensor:
        seg_map = np.full(mask.shape[:-1], -1)
        for index, color in enumerate(COLOR_LIST):
            seg_map[np.sum(mask == color, axis=2) == 3] = index
        assert (seg_map != -1).all()
        return seg_map

    @staticmethod
    def postprocess(result: torch.Tensor) -> np.ndarray:
        result = result.permute(0, 2, 3, 1)
        result = result.detach().cpu().numpy()
        result = result * 255
        result = np.asarray(result[0, :, :, :], dtype=np.uint8)
        return result

    def process_pose_image(self, pose_image: PIL.Image.Image) -> None:
        if pose_image is None:
            return
        data = self.preprocess_pose_image(pose_image)
        self.model.feed_pose_data(data)

    def generate_label_image(self, shape_text: str) -> np.ndarray:
        shape_attributes = generate_shape_attributes(shape_text)
        shape_attributes = torch.LongTensor(shape_attributes).unsqueeze(0)
        self.model.feed_shape_attributes(shape_attributes)
        self.model.generate_parsing_map()
        self.model.generate_quantized_segm()
        colored_segm = self.model.palette_result(self.model.segm[0].cpu())

        mask = colored_segm.copy()
        seg_map = self.process_mask(mask)
        self.model.segm = torch.from_numpy(seg_map).unsqueeze(0).unsqueeze(
            0).to(self.model.device)
        self.model.generate_quantized_segm()
        return colored_segm

    def generate_human(self, texture_text: str, sample_steps: int,
                       seed: int) -> np.ndarray:
        set_random_seed(seed)

        texture_attributes = generate_texture_attributes(texture_text)
        texture_attributes = torch.LongTensor(texture_attributes)
        self.model.feed_texture_attributes(texture_attributes)
        self.model.generate_texture_map()

        self.model.sample_steps = sample_steps
        out = self.model.sample_and_refine()
        res = self.postprocess(out)
        return res