File size: 19,206 Bytes
f39e999
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
# Copyright (c) 2021, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.

import click
import pickle
import re
import copy
import numpy as np
import torch
import dnnlib
from torch_utils import misc

#----------------------------------------------------------------------------

# !!! custom
def load_network_pkl(f, force_fp16=False, custom=False, **ex_kwargs):
# def load_network_pkl(f, force_fp16=False):
    data = _LegacyUnpickler(f).load()
    # data = pickle.load(f, encoding='latin1')

    # Legacy TensorFlow pickle => convert.
    if isinstance(data, tuple) and len(data) == 3 and all(isinstance(net, _TFNetworkStub) for net in data):
        tf_G, tf_D, tf_Gs = data
        G = convert_tf_generator(tf_G, custom=custom, **ex_kwargs)
        D = convert_tf_discriminator(tf_D)
        G_ema = convert_tf_generator(tf_Gs, custom=custom, **ex_kwargs)
        data = dict(G=G, D=D, G_ema=G_ema)
# !!! custom
        assert isinstance(data['G'], torch.nn.Module)
        assert isinstance(data['D'], torch.nn.Module)
        nets = ['G', 'D', 'G_ema']
    elif isinstance(data, _TFNetworkStub):
        G_ema = convert_tf_generator(data, custom=custom, **ex_kwargs)
        data = dict(G_ema=G_ema)
        nets = ['G_ema']
    else:
# !!! custom
        if custom is True:
            G_ema = custom_generator(data, **ex_kwargs)
            data = dict(G_ema=G_ema)
            nets = ['G_ema']
        else:
            nets = []
            for name in ['G', 'D', 'G_ema']:
                if name in data.keys():
                    nets.append(name)
        # print(nets)

    # Add missing fields.
    if 'training_set_kwargs' not in data:
        data['training_set_kwargs'] = None
    if 'augment_pipe' not in data:
        data['augment_pipe'] = None

    # Validate contents.
    assert isinstance(data['G_ema'], torch.nn.Module)
    assert isinstance(data['training_set_kwargs'], (dict, type(None)))
    assert isinstance(data['augment_pipe'], (torch.nn.Module, type(None)))

    # Force FP16.
    if force_fp16:
        for key in nets: # !!! custom
            old = data[key]
            kwargs = copy.deepcopy(old.init_kwargs)
            if key.startswith('G'):
                kwargs.synthesis_kwargs = dnnlib.EasyDict(kwargs.get('synthesis_kwargs', {}))
                kwargs.synthesis_kwargs.num_fp16_res = 4
                kwargs.synthesis_kwargs.conv_clamp = 256
            if key.startswith('D'):
                kwargs.num_fp16_res = 4
                kwargs.conv_clamp = 256
            if kwargs != old.init_kwargs:
                new = type(old)(**kwargs).eval().requires_grad_(False)
                misc.copy_params_and_buffers(old, new, require_all=True)
                data[key] = new
    return data

#----------------------------------------------------------------------------

class _TFNetworkStub(dnnlib.EasyDict):
    pass

class _LegacyUnpickler(pickle.Unpickler):
    def find_class(self, module, name):
        if module == 'dnnlib.tflib.network' and name == 'Network':
            return _TFNetworkStub
        return super().find_class(module, name)

#----------------------------------------------------------------------------

def _collect_tf_params(tf_net):
    # pylint: disable=protected-access
    tf_params = dict()
    def recurse(prefix, tf_net):
        for name, value in tf_net.variables:
            tf_params[prefix + name] = value
        for name, comp in tf_net.components.items():
            recurse(prefix + name + '/', comp)
    recurse('', tf_net)
    return tf_params

#----------------------------------------------------------------------------

def _populate_module_params(module, *patterns):
    for name, tensor in misc.named_params_and_buffers(module):
        found = False
        value = None
        for pattern, value_fn in zip(patterns[0::2], patterns[1::2]):
            match = re.fullmatch(pattern, name)
            if match:
                found = True
                if value_fn is not None:
                    value = value_fn(*match.groups())
                break
        try:
            assert found
            if value is not None:
                tensor.copy_(torch.from_numpy(np.array(value)))
        except:
            print(name, list(tensor.shape))
            raise

#----------------------------------------------------------------------------

# !!! custom
def custom_generator(data, **ex_kwargs):
    from training import stylegan2_multi as networks
    try: # saved? (with new fix)
        fmap_base = data['G_ema'].synthesis.fmap_base
    except: # default from original configs
        fmap_base = 32768 if data['G_ema'].img_resolution >= 512 else 16384
    kwargs = dnnlib.EasyDict(
        z_dim           = data['G_ema'].z_dim,
        c_dim           = data['G_ema'].c_dim,
        w_dim           = data['G_ema'].w_dim,
        img_resolution  = data['G_ema'].img_resolution,
        img_channels    = data['G_ema'].img_channels,
        init_res        = [4,4], # hacky
        mapping_kwargs  = dnnlib.EasyDict(num_layers = data['G_ema'].mapping.num_layers),
        synthesis_kwargs = dnnlib.EasyDict(channel_base = fmap_base, **ex_kwargs),
    )
    G_out = networks.Generator(**kwargs).eval().requires_grad_(False)
    misc.copy_params_and_buffers(data['G_ema'], G_out, require_all=False)
    return G_out

# !!! custom
def convert_tf_generator(tf_G, custom=False, **ex_kwargs):
# def convert_tf_generator(tf_G):
    if tf_G.version < 4:
        raise ValueError('TensorFlow pickle version too low')

    # Collect kwargs.
    tf_kwargs = tf_G.static_kwargs
    known_kwargs = set()
    def kwarg(tf_name, default=None, none=None):
        known_kwargs.add(tf_name)
        val = tf_kwargs.get(tf_name, default)
        return val if val is not None else none

    # Convert kwargs.
    kwargs = dnnlib.EasyDict(
        z_dim                   = kwarg('latent_size',          512),
        c_dim                   = kwarg('label_size',           0),
        w_dim                   = kwarg('dlatent_size',         512),
        img_resolution          = kwarg('resolution',           1024),
        img_channels            = kwarg('num_channels',         3),
        mapping_kwargs = dnnlib.EasyDict(
            num_layers          = kwarg('mapping_layers',       8),
            embed_features      = kwarg('label_fmaps',          None),
            layer_features      = kwarg('mapping_fmaps',        None),
            activation          = kwarg('mapping_nonlinearity', 'lrelu'),
            lr_multiplier       = kwarg('mapping_lrmul',        0.01),
            w_avg_beta          = kwarg('w_avg_beta',           0.995,  none=1),
        ),
        synthesis_kwargs = dnnlib.EasyDict(
            channel_base        = kwarg('fmap_base',            16384) * 2,
            channel_max         = kwarg('fmap_max',             512),
            num_fp16_res        = kwarg('num_fp16_res',         0),
            conv_clamp          = kwarg('conv_clamp',           None),
            architecture        = kwarg('architecture',         'skip'),
            resample_filter     = kwarg('resample_kernel',      [1,3,3,1]),
            use_noise           = kwarg('use_noise',            True),
            activation          = kwarg('nonlinearity',         'lrelu'),
        ),
# !!! custom
        # init_res                = kwarg('init_res',            [4,4]),
    )

    # Check for unknown kwargs.
    kwarg('truncation_psi')
    kwarg('truncation_cutoff')
    kwarg('style_mixing_prob')
    kwarg('structure')
    unknown_kwargs = list(set(tf_kwargs.keys()) - known_kwargs)
# !!! custom
    if custom:
        kwargs.init_res = [4,4]
        kwargs.synthesis_kwargs = dnnlib.EasyDict(**kwargs.synthesis_kwargs, **ex_kwargs)
    if len(unknown_kwargs) > 0:
        print('Unknown TensorFlow data! This may result in problems with your converted model.')
        print(unknown_kwargs)
        #raise ValueError('Unknown TensorFlow kwargs:', unknown_kwargs)
        # raise ValueError('Unknown TensorFlow kwarg', unknown_kwargs[0])
    # try: 
        # if ex_kwargs['verbose'] is True: print(kwargs.synthesis_kwargs)
    # except: pass

    # Collect params.
    tf_params = _collect_tf_params(tf_G)
    for name, value in list(tf_params.items()):
        match = re.fullmatch(r'ToRGB_lod(\d+)/(.*)', name)
        if match:
            r = kwargs.img_resolution // (2 ** int(match.group(1)))
            tf_params[f'{r}x{r}/ToRGB/{match.group(2)}'] = value
            kwargs.synthesis.kwargs.architecture = 'orig'
    #for name, value in tf_params.items(): print(f'{name:<50s}{list(value.shape)}')

    # Convert params.
    if custom:
        from training import stylegan2_multi as networks
    else:
        from training import networks
    G = networks.Generator(**kwargs).eval().requires_grad_(False)
    # pylint: disable=unnecessary-lambda
    _populate_module_params(G,
        r'mapping\.w_avg',                                  lambda:     tf_params[f'dlatent_avg'],
        r'mapping\.embed\.weight',                          lambda:     tf_params[f'mapping/LabelEmbed/weight'].transpose(),
        r'mapping\.embed\.bias',                            lambda:     tf_params[f'mapping/LabelEmbed/bias'],
        r'mapping\.fc(\d+)\.weight',                        lambda i:   tf_params[f'mapping/Dense{i}/weight'].transpose(),
        r'mapping\.fc(\d+)\.bias',                          lambda i:   tf_params[f'mapping/Dense{i}/bias'],
        r'synthesis\.b4\.const',                            lambda:     tf_params[f'synthesis/4x4/Const/const'][0],
        r'synthesis\.b4\.conv1\.weight',                    lambda:     tf_params[f'synthesis/4x4/Conv/weight'].transpose(3, 2, 0, 1),
        r'synthesis\.b4\.conv1\.bias',                      lambda:     tf_params[f'synthesis/4x4/Conv/bias'],
        r'synthesis\.b4\.conv1\.noise_const',               lambda:     tf_params[f'synthesis/noise0'][0, 0],
        r'synthesis\.b4\.conv1\.noise_strength',            lambda:     tf_params[f'synthesis/4x4/Conv/noise_strength'],
        r'synthesis\.b4\.conv1\.affine\.weight',            lambda:     tf_params[f'synthesis/4x4/Conv/mod_weight'].transpose(),
        r'synthesis\.b4\.conv1\.affine\.bias',              lambda:     tf_params[f'synthesis/4x4/Conv/mod_bias'] + 1,
        r'synthesis\.b(\d+)\.conv0\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/weight'][::-1, ::-1].transpose(3, 2, 0, 1),
        r'synthesis\.b(\d+)\.conv0\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/bias'],
        r'synthesis\.b(\d+)\.conv0\.noise_const',           lambda r:   tf_params[f'synthesis/noise{int(np.log2(int(r)))*2-5}'][0, 0],
        r'synthesis\.b(\d+)\.conv0\.noise_strength',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/noise_strength'],
        r'synthesis\.b(\d+)\.conv0\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/mod_weight'].transpose(),
        r'synthesis\.b(\d+)\.conv0\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/mod_bias'] + 1,
        r'synthesis\.b(\d+)\.conv1\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/weight'].transpose(3, 2, 0, 1),
        r'synthesis\.b(\d+)\.conv1\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/bias'],
        r'synthesis\.b(\d+)\.conv1\.noise_const',           lambda r:   tf_params[f'synthesis/noise{int(np.log2(int(r)))*2-4}'][0, 0],
        r'synthesis\.b(\d+)\.conv1\.noise_strength',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/noise_strength'],
        r'synthesis\.b(\d+)\.conv1\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/mod_weight'].transpose(),
        r'synthesis\.b(\d+)\.conv1\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/mod_bias'] + 1,
        r'synthesis\.b(\d+)\.torgb\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/weight'].transpose(3, 2, 0, 1),
        r'synthesis\.b(\d+)\.torgb\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/bias'],
        r'synthesis\.b(\d+)\.torgb\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/mod_weight'].transpose(),
        r'synthesis\.b(\d+)\.torgb\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/mod_bias'] + 1,
        r'synthesis\.b(\d+)\.skip\.weight',                 lambda r:   tf_params[f'synthesis/{r}x{r}/Skip/weight'][::-1, ::-1].transpose(3, 2, 0, 1),
        r'.*\.resample_filter',                             None,
    )
    return G

#----------------------------------------------------------------------------

def convert_tf_discriminator(tf_D):
    if tf_D.version < 4:
        raise ValueError('TensorFlow pickle version too low')

    # Collect kwargs.
    tf_kwargs = tf_D.static_kwargs
    known_kwargs = set()
    def kwarg(tf_name, default=None):
        known_kwargs.add(tf_name)
        return tf_kwargs.get(tf_name, default)

    # Convert kwargs.
    kwargs = dnnlib.EasyDict(
        c_dim                   = kwarg('label_size',           0),
        img_resolution          = kwarg('resolution',           1024),
        img_channels            = kwarg('num_channels',         3),
        architecture            = kwarg('architecture',         'resnet'),
        channel_base            = kwarg('fmap_base',            16384) * 2,
        channel_max             = kwarg('fmap_max',             512),
        num_fp16_res            = kwarg('num_fp16_res',         0),
        conv_clamp              = kwarg('conv_clamp',           None),
        cmap_dim                = kwarg('mapping_fmaps',        None),
        block_kwargs = dnnlib.EasyDict(
            activation          = kwarg('nonlinearity',         'lrelu'),
            resample_filter     = kwarg('resample_kernel',      [1,3,3,1]),
            freeze_layers       = kwarg('freeze_layers',        0),
        ),
        mapping_kwargs = dnnlib.EasyDict(
            num_layers          = kwarg('mapping_layers',       0),
            embed_features      = kwarg('mapping_fmaps',        None),
            layer_features      = kwarg('mapping_fmaps',        None),
            activation          = kwarg('nonlinearity',         'lrelu'),
            lr_multiplier       = kwarg('mapping_lrmul',        0.1),
        ),
        epilogue_kwargs = dnnlib.EasyDict(
            mbstd_group_size    = kwarg('mbstd_group_size',     None),
            mbstd_num_channels  = kwarg('mbstd_num_features',   1),
            activation          = kwarg('nonlinearity',         'lrelu'),
        ),
# !!! custom
        # init_res                = kwarg('init_res',            [4,4]),
    )

    # Check for unknown kwargs.
    kwarg('structure')
    unknown_kwargs = list(set(tf_kwargs.keys()) - known_kwargs)
    if len(unknown_kwargs) > 0:
        print('Unknown TensorFlow data! This may result in problems with your converted model.')
        print(unknown_kwargs)
        # originally this repo threw errors:
        # raise ValueError('Unknown TensorFlow kwarg', unknown_kwargs[0])

    # Collect params.
    tf_params = _collect_tf_params(tf_D)
    for name, value in list(tf_params.items()):
        match = re.fullmatch(r'FromRGB_lod(\d+)/(.*)', name)
        if match:
            r = kwargs.img_resolution // (2 ** int(match.group(1)))
            tf_params[f'{r}x{r}/FromRGB/{match.group(2)}'] = value
            kwargs.architecture = 'orig'
    #for name, value in tf_params.items(): print(f'{name:<50s}{list(value.shape)}')

    # Convert params.
    from training import networks
    D = networks.Discriminator(**kwargs).eval().requires_grad_(False)
    # pylint: disable=unnecessary-lambda
    _populate_module_params(D,
        r'b(\d+)\.fromrgb\.weight',     lambda r:       tf_params[f'{r}x{r}/FromRGB/weight'].transpose(3, 2, 0, 1),
        r'b(\d+)\.fromrgb\.bias',       lambda r:       tf_params[f'{r}x{r}/FromRGB/bias'],
        r'b(\d+)\.conv(\d+)\.weight',   lambda r, i:    tf_params[f'{r}x{r}/Conv{i}{["","_down"][int(i)]}/weight'].transpose(3, 2, 0, 1),
        r'b(\d+)\.conv(\d+)\.bias',     lambda r, i:    tf_params[f'{r}x{r}/Conv{i}{["","_down"][int(i)]}/bias'],
        r'b(\d+)\.skip\.weight',        lambda r:       tf_params[f'{r}x{r}/Skip/weight'].transpose(3, 2, 0, 1),
        r'mapping\.embed\.weight',      lambda:         tf_params[f'LabelEmbed/weight'].transpose(),
        r'mapping\.embed\.bias',        lambda:         tf_params[f'LabelEmbed/bias'],
        r'mapping\.fc(\d+)\.weight',    lambda i:       tf_params[f'Mapping{i}/weight'].transpose(),
        r'mapping\.fc(\d+)\.bias',      lambda i:       tf_params[f'Mapping{i}/bias'],
        r'b4\.conv\.weight',            lambda:         tf_params[f'4x4/Conv/weight'].transpose(3, 2, 0, 1),
        r'b4\.conv\.bias',              lambda:         tf_params[f'4x4/Conv/bias'],
        r'b4\.fc\.weight',              lambda:         tf_params[f'4x4/Dense0/weight'].transpose(),
        r'b4\.fc\.bias',                lambda:         tf_params[f'4x4/Dense0/bias'],
        r'b4\.out\.weight',             lambda:         tf_params[f'Output/weight'].transpose(),
        r'b4\.out\.bias',               lambda:         tf_params[f'Output/bias'],
        r'.*\.resample_filter',         None,
    )
    return D

#----------------------------------------------------------------------------

@click.command()
@click.option('--source', help='Input pickle', required=True, metavar='PATH')
@click.option('--dest', help='Output pickle', required=True, metavar='PATH')
@click.option('--force-fp16', help='Force the networks to use FP16', type=bool, default=False, metavar='BOOL', show_default=True)
def convert_network_pickle(source, dest, force_fp16):
    """Convert legacy network pickle into the native PyTorch format.

    The tool is able to load the main network configurations exported using the TensorFlow version of StyleGAN2 or StyleGAN2-ADA.
    It does not support e.g. StyleGAN2-ADA comparison methods, StyleGAN2 configs A-D, or StyleGAN1 networks.

    Example:

    \b
    python legacy.py \\
        --source=https://nvlabs-fi-cdn.nvidia.com/stylegan2/networks/stylegan2-cat-config-f.pkl \\
        --dest=stylegan2-cat-config-f.pkl
    """
    print(f'Loading "{source}"...')
    with dnnlib.util.open_url(source) as f:
        data = load_network_pkl(f, force_fp16=force_fp16)
    print(f'Saving "{dest}"...')
    with open(dest, 'wb') as f:
        pickle.dump(data, f)
    print('Done.')

#----------------------------------------------------------------------------

if __name__ == "__main__":
    convert_network_pickle() # pylint: disable=no-value-for-parameter

#----------------------------------------------------------------------------