forked from NVlabs/stylegan
-
Notifications
You must be signed in to change notification settings - Fork 0
/
generate_figures.py
executable file
·156 lines (130 loc) · 8.71 KB
/
generate_figures.py
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
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
#
# This work is licensed under the Creative Commons Attribution-NonCommercial
# 4.0 International License. To view a copy of this license, visit
# http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
# Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
"""Minimal script for reproducing the figures of the StyleGAN paper using pre-trained generators."""
import os
import sys
import pickle
import numpy as np
import PIL.Image
import dnnlib
import dnnlib.tflib as tflib
import config
#----------------------------------------------------------------------------
# Helpers for loading and using pre-trained generators.
url_ffhq = 'https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ' # karras2019stylegan-ffhq-1024x1024.pkl
url_celebahq = 'https://drive.google.com/uc?id=1MGqJl28pN4t7SAtSrPdSRJSQJqahkzUf' # karras2019stylegan-celebahq-1024x1024.pkl
url_bedrooms = 'https://drive.google.com/uc?id=1MOSKeGF0FJcivpBI7s63V9YHloUTORiF' # karras2019stylegan-bedrooms-256x256.pkl
url_cars = 'https://drive.google.com/uc?id=1MJ6iCfNtMIRicihwRorsM3b7mmtmK9c3' # karras2019stylegan-cars-512x384.pkl
url_cats = 'https://drive.google.com/uc?id=1MQywl0FNt6lHu8E_EUqnRbviagS7fbiJ' # karras2019stylegan-cats-256x256.pkl
synthesis_kwargs = dict(output_transform=dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True), minibatch_size=8, truncation_psi=0.7)
_Gs_cache = dict()
def load_Gs(url):
_G, _D, Gs = pickle.load(open(sys.argv[1], "rb"))
return Gs
#----------------------------------------------------------------------------
# Figures 2, 3, 10, 11, 12: Multi-resolution grid of uncurated result images.
def draw_uncurated_result_figure(png, Gs, cx, cy, cw, ch, rows, lods, seed):
print(png)
latents = np.random.RandomState(seed).randn(sum(rows * 2**lod for lod in lods), Gs.input_shape[1])
images = Gs.run(latents, None, **synthesis_kwargs) # [seed, y, x, rgb]
canvas = PIL.Image.new('RGB', (sum(cw // 2**lod for lod in lods), ch * rows), 'white')
image_iter = iter(list(images))
for col, lod in enumerate(lods):
for row in range(rows * 2**lod):
image = PIL.Image.fromarray(next(image_iter), 'RGB')
image = image.crop((cx, cy, cx + cw, cy + ch))
image = image.resize((cw // 2**lod, ch // 2**lod), PIL.Image.ANTIALIAS)
canvas.paste(image, (sum(cw // 2**lod for lod in lods[:col]), row * ch // 2**lod))
canvas.save(png)
#----------------------------------------------------------------------------
# Figure 3: Style mixing.
def draw_style_mixing_figure(png, Gs, w, h, src_seeds, dst_seeds, style_ranges):
print(png)
src_latents = np.stack(np.random.RandomState(seed).randn(Gs.input_shape[1]) for seed in src_seeds)
dst_latents = np.stack(np.random.RandomState(seed).randn(Gs.input_shape[1]) for seed in dst_seeds)
src_dlatents = Gs.components.mapping.run(src_latents, None) # [seed, layer, component]
dst_dlatents = Gs.components.mapping.run(dst_latents, None) # [seed, layer, component]
src_images = Gs.components.synthesis.run(src_dlatents, randomize_noise=False, **synthesis_kwargs)
dst_images = Gs.components.synthesis.run(dst_dlatents, randomize_noise=False, **synthesis_kwargs)
canvas = PIL.Image.new('RGB', (w * (len(src_seeds) + 1), h * (len(dst_seeds) + 1)), 'white')
for col, src_image in enumerate(list(src_images)):
canvas.paste(PIL.Image.fromarray(src_image, 'RGB'), ((col + 1) * w, 0))
for row, dst_image in enumerate(list(dst_images)):
canvas.paste(PIL.Image.fromarray(dst_image, 'RGB'), (0, (row + 1) * h))
row_dlatents = np.stack([dst_dlatents[row]] * len(src_seeds))
row_dlatents[:, style_ranges[row]] = src_dlatents[:, style_ranges[row]]
row_images = Gs.components.synthesis.run(row_dlatents, randomize_noise=False, **synthesis_kwargs)
for col, image in enumerate(list(row_images)):
canvas.paste(PIL.Image.fromarray(image, 'RGB'), ((col + 1) * w, (row + 1) * h))
canvas.save(png)
#----------------------------------------------------------------------------
# Figure 4: Noise detail.
def draw_noise_detail_figure(png, Gs, w, h, num_samples, seeds):
print(png)
canvas = PIL.Image.new('RGB', (w * 3, h * len(seeds)), 'white')
for row, seed in enumerate(seeds):
latents = np.stack([np.random.RandomState(seed).randn(Gs.input_shape[1])] * num_samples)
images = Gs.run(latents, None, **synthesis_kwargs)
canvas.paste(PIL.Image.fromarray(images[0], 'RGB'), (0, row * h))
for i in range(4):
crop = PIL.Image.fromarray(images[i + 1], 'RGB')
crop = crop.crop((650, 180, 906, 436))
crop = crop.resize((w//2, h//2), PIL.Image.NEAREST)
canvas.paste(crop, (w + (i%2) * w//2, row * h + (i//2) * h//2))
diff = np.std(np.mean(images, axis=3), axis=0) * 4
diff = np.clip(diff + 0.5, 0, 255).astype(np.uint8)
canvas.paste(PIL.Image.fromarray(diff, 'L'), (w * 2, row * h))
canvas.save(png)
#----------------------------------------------------------------------------
# Figure 5: Noise components.
def draw_noise_components_figure(png, Gs, w, h, seeds, noise_ranges, flips):
print(png)
Gsc = Gs.clone()
noise_vars = [var for name, var in Gsc.components.synthesis.vars.items() if name.startswith('noise')]
noise_pairs = list(zip(noise_vars, tflib.run(noise_vars))) # [(var, val), ...]
latents = np.stack(np.random.RandomState(seed).randn(Gs.input_shape[1]) for seed in seeds)
all_images = []
for noise_range in noise_ranges:
tflib.set_vars({var: val * (1 if i in noise_range else 0) for i, (var, val) in enumerate(noise_pairs)})
range_images = Gsc.run(latents, None, randomize_noise=False, **synthesis_kwargs)
range_images[flips, :, :] = range_images[flips, :, ::-1]
all_images.append(list(range_images))
canvas = PIL.Image.new('RGB', (w * 2, h * 2), 'white')
for col, col_images in enumerate(zip(*all_images)):
canvas.paste(PIL.Image.fromarray(col_images[0], 'RGB').crop((0, 0, w//2, h)), (col * w, 0))
canvas.paste(PIL.Image.fromarray(col_images[1], 'RGB').crop((w//2, 0, w, h)), (col * w + w//2, 0))
canvas.paste(PIL.Image.fromarray(col_images[2], 'RGB').crop((0, 0, w//2, h)), (col * w, h))
canvas.paste(PIL.Image.fromarray(col_images[3], 'RGB').crop((w//2, 0, w, h)), (col * w + w//2, h))
canvas.save(png)
#----------------------------------------------------------------------------
# Figure 8: Truncation trick.
def draw_truncation_trick_figure(png, Gs, w, h, seeds, psis):
print(png)
latents = np.stack(np.random.RandomState(seed).randn(Gs.input_shape[1]) for seed in seeds)
dlatents = Gs.components.mapping.run(latents, None) # [seed, layer, component]
dlatent_avg = Gs.get_var('dlatent_avg') # [component]
canvas = PIL.Image.new('RGB', (w * len(psis), h * len(seeds)), 'white')
for row, dlatent in enumerate(list(dlatents)):
row_dlatents = (dlatent[np.newaxis] - dlatent_avg) * np.reshape(psis, [-1, 1, 1]) + dlatent_avg
row_images = Gs.components.synthesis.run(row_dlatents, randomize_noise=False, **synthesis_kwargs)
for col, image in enumerate(list(row_images)):
canvas.paste(PIL.Image.fromarray(image, 'RGB'), (col * w, row * h))
canvas.save(png)
#----------------------------------------------------------------------------
# Main program.
def main():
tflib.init_tf()
os.makedirs(config.result_dir, exist_ok=True)
draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure02-uncurated-ffhq.png'), load_Gs(url_ffhq), cx=0, cy=0, cw=512, ch=512, rows=3, lods=[0,1,2,2,3,3], seed=5)
draw_style_mixing_figure(os.path.join(config.result_dir, 'figure03-style-mixing.png'), load_Gs(url_ffhq), w=512, h=512, src_seeds=[639,701,687,615,2268], dst_seeds=[888,829,1898,1733,1614,845], style_ranges=[range(0,4)]*3+[range(4,8)]*2+[range(8,16)])
draw_noise_detail_figure(os.path.join(config.result_dir, 'figure04-noise-detail.png'), load_Gs(url_ffhq), w=512, h=512, num_samples=100, seeds=[1157,1012])
draw_noise_components_figure(os.path.join(config.result_dir, 'figure05-noise-components.png'), load_Gs(url_ffhq), w=512, h=512, seeds=[1967,1555], noise_ranges=[range(0, 18), range(0, 0), range(8, 18), range(0, 8)], flips=[1])
draw_truncation_trick_figure(os.path.join(config.result_dir, 'figure08-truncation-trick.png'), load_Gs(url_ffhq), w=512, h=512, seeds=[91,388, 389, 390, 391, 392, 393, 394, 395, 396], psis=[1, 0.7, 0.5, 0.25, 0, -0.25, -0.5, -1])
#----------------------------------------------------------------------------
if __name__ == "__main__":
main()
#----------------------------------------------------------------------------