File size: 15,565 Bytes
dc1ad90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
385
386
387
388
389
390
391
392
393
394
395
import os, yaml, pickle, shutil, tarfile, glob
import cv2
import albumentations
import PIL
import numpy as np
import torchvision.transforms.functional as TF
from omegaconf import OmegaConf
from functools import partial
from PIL import Image
from tqdm import tqdm
from torch.utils.data import Dataset, Subset

import taming.data.utils as tdu
from taming.data.imagenet import str_to_indices, give_synsets_from_indices, download, retrieve
from taming.data.imagenet import ImagePaths

from ldm.modules.image_degradation import degradation_fn_bsr, degradation_fn_bsr_light


def synset2idx(path_to_yaml="data/index_synset.yaml"):
    with open(path_to_yaml) as f:
        di2s = yaml.load(f)
    return dict((v,k) for k,v in di2s.items())


class ImageNetBase(Dataset):
    def __init__(self, config=None):
        self.config = config or OmegaConf.create()
        if not type(self.config)==dict:
            self.config = OmegaConf.to_container(self.config)
        self.keep_orig_class_label = self.config.get("keep_orig_class_label", False)
        self.process_images = True  # if False we skip loading & processing images and self.data contains filepaths
        self._prepare()
        self._prepare_synset_to_human()
        self._prepare_idx_to_synset()
        self._prepare_human_to_integer_label()
        self._load()

    def __len__(self):
        return len(self.data)

    def __getitem__(self, i):
        return self.data[i]

    def _prepare(self):
        raise NotImplementedError()

    def _filter_relpaths(self, relpaths):
        ignore = set([
            "n06596364_9591.JPEG",
        ])
        relpaths = [rpath for rpath in relpaths if not rpath.split("/")[-1] in ignore]
        if "sub_indices" in self.config:
            indices = str_to_indices(self.config["sub_indices"])
            synsets = give_synsets_from_indices(indices, path_to_yaml=self.idx2syn)  # returns a list of strings
            self.synset2idx = synset2idx(path_to_yaml=self.idx2syn)
            files = []
            for rpath in relpaths:
                syn = rpath.split("/")[0]
                if syn in synsets:
                    files.append(rpath)
            return files
        else:
            return relpaths

    def _prepare_synset_to_human(self):
        SIZE = 2655750
        URL = "https://heibox.uni-heidelberg.de/f/9f28e956cd304264bb82/?dl=1"
        self.human_dict = os.path.join(self.root, "synset_human.txt")
        if (not os.path.exists(self.human_dict) or
                not os.path.getsize(self.human_dict)==SIZE):
            download(URL, self.human_dict)

    def _prepare_idx_to_synset(self):
        URL = "https://heibox.uni-heidelberg.de/f/d835d5b6ceda4d3aa910/?dl=1"
        self.idx2syn = os.path.join(self.root, "index_synset.yaml")
        if (not os.path.exists(self.idx2syn)):
            download(URL, self.idx2syn)

    def _prepare_human_to_integer_label(self):
        URL = "https://heibox.uni-heidelberg.de/f/2362b797d5be43b883f6/?dl=1"
        self.human2integer = os.path.join(self.root, "imagenet1000_clsidx_to_labels.txt")
        if (not os.path.exists(self.human2integer)):
            download(URL, self.human2integer)
        with open(self.human2integer, "r") as f:
            lines = f.read().splitlines()
            assert len(lines) == 1000
            self.human2integer_dict = dict()
            for line in lines:
                value, key = line.split(":")
                self.human2integer_dict[key] = int(value)

    def _load(self):
        with open(self.txt_filelist, "r") as f:
            self.relpaths = f.read().splitlines()
            l1 = len(self.relpaths)
            self.relpaths = self._filter_relpaths(self.relpaths)
            print("Removed {} files from filelist during filtering.".format(l1 - len(self.relpaths)))

        self.synsets = [p.split("/")[0] for p in self.relpaths]
        self.abspaths = [os.path.join(self.datadir, p) for p in self.relpaths]

        unique_synsets = np.unique(self.synsets)
        class_dict = dict((synset, i) for i, synset in enumerate(unique_synsets))
        if not self.keep_orig_class_label:
            self.class_labels = [class_dict[s] for s in self.synsets]
        else:
            self.class_labels = [self.synset2idx[s] for s in self.synsets]

        with open(self.human_dict, "r") as f:
            human_dict = f.read().splitlines()
            human_dict = dict(line.split(maxsplit=1) for line in human_dict)

        self.human_labels = [human_dict[s] for s in self.synsets]

        labels = {
            "relpath": np.array(self.relpaths),
            "synsets": np.array(self.synsets),
            "class_label": np.array(self.class_labels),
            "human_label": np.array(self.human_labels),
        }

        if self.process_images:
            self.size = retrieve(self.config, "size", default=256)
            self.data = ImagePaths(self.abspaths,
                                   labels=labels,
                                   size=self.size,
                                   random_crop=self.random_crop,
                                   )
        else:
            self.data = self.abspaths


class ImageNetTrain(ImageNetBase):
    NAME = "ILSVRC2012_train"
    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
    AT_HASH = "a306397ccf9c2ead27155983c254227c0fd938e2"
    FILES = [
        "ILSVRC2012_img_train.tar",
    ]
    SIZES = [
        147897477120,
    ]

    def __init__(self, process_images=True, data_root=None, **kwargs):
        self.process_images = process_images
        self.data_root = data_root
        super().__init__(**kwargs)

    def _prepare(self):
        if self.data_root:
            self.root = os.path.join(self.data_root, self.NAME)
        else:
            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)

        self.datadir = os.path.join(self.root, "data")
        self.txt_filelist = os.path.join(self.root, "filelist.txt")
        self.expected_length = 1281167
        self.random_crop = retrieve(self.config, "ImageNetTrain/random_crop",
                                    default=True)
        if not tdu.is_prepared(self.root):
            # prep
            print("Preparing dataset {} in {}".format(self.NAME, self.root))

            datadir = self.datadir
            if not os.path.exists(datadir):
                path = os.path.join(self.root, self.FILES[0])
                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
                    import academictorrents as at
                    atpath = at.get(self.AT_HASH, datastore=self.root)
                    assert atpath == path

                print("Extracting {} to {}".format(path, datadir))
                os.makedirs(datadir, exist_ok=True)
                with tarfile.open(path, "r:") as tar:
                    tar.extractall(path=datadir)

                print("Extracting sub-tars.")
                subpaths = sorted(glob.glob(os.path.join(datadir, "*.tar")))
                for subpath in tqdm(subpaths):
                    subdir = subpath[:-len(".tar")]
                    os.makedirs(subdir, exist_ok=True)
                    with tarfile.open(subpath, "r:") as tar:
                        tar.extractall(path=subdir)

            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
            filelist = sorted(filelist)
            filelist = "\n".join(filelist)+"\n"
            with open(self.txt_filelist, "w") as f:
                f.write(filelist)

            tdu.mark_prepared(self.root)


class ImageNetValidation(ImageNetBase):
    NAME = "ILSVRC2012_validation"
    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
    AT_HASH = "5d6d0df7ed81efd49ca99ea4737e0ae5e3a5f2e5"
    VS_URL = "https://heibox.uni-heidelberg.de/f/3e0f6e9c624e45f2bd73/?dl=1"
    FILES = [
        "ILSVRC2012_img_val.tar",
        "validation_synset.txt",
    ]
    SIZES = [
        6744924160,
        1950000,
    ]

    def __init__(self, process_images=True, data_root=None, **kwargs):
        self.data_root = data_root
        self.process_images = process_images
        super().__init__(**kwargs)

    def _prepare(self):
        if self.data_root:
            self.root = os.path.join(self.data_root, self.NAME)
        else:
            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
        self.datadir = os.path.join(self.root, "data")
        self.txt_filelist = os.path.join(self.root, "filelist.txt")
        self.expected_length = 50000
        self.random_crop = retrieve(self.config, "ImageNetValidation/random_crop",
                                    default=False)
        if not tdu.is_prepared(self.root):
            # prep
            print("Preparing dataset {} in {}".format(self.NAME, self.root))

            datadir = self.datadir
            if not os.path.exists(datadir):
                path = os.path.join(self.root, self.FILES[0])
                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
                    import academictorrents as at
                    atpath = at.get(self.AT_HASH, datastore=self.root)
                    assert atpath == path

                print("Extracting {} to {}".format(path, datadir))
                os.makedirs(datadir, exist_ok=True)
                with tarfile.open(path, "r:") as tar:
                    tar.extractall(path=datadir)

                vspath = os.path.join(self.root, self.FILES[1])
                if not os.path.exists(vspath) or not os.path.getsize(vspath)==self.SIZES[1]:
                    download(self.VS_URL, vspath)

                with open(vspath, "r") as f:
                    synset_dict = f.read().splitlines()
                    synset_dict = dict(line.split() for line in synset_dict)

                print("Reorganizing into synset folders")
                synsets = np.unique(list(synset_dict.values()))
                for s in synsets:
                    os.makedirs(os.path.join(datadir, s), exist_ok=True)
                for k, v in synset_dict.items():
                    src = os.path.join(datadir, k)
                    dst = os.path.join(datadir, v)
                    shutil.move(src, dst)

            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
            filelist = sorted(filelist)
            filelist = "\n".join(filelist)+"\n"
            with open(self.txt_filelist, "w") as f:
                f.write(filelist)

            tdu.mark_prepared(self.root)



class ImageNetSR(Dataset):
    def __init__(self, size=None,
                 degradation=None, downscale_f=4, min_crop_f=0.5, max_crop_f=1.,
                 random_crop=True):
        """
        Imagenet Superresolution Dataloader
        Performs following ops in order:
        1.  crops a crop of size s from image either as random or center crop
        2.  resizes crop to size with cv2.area_interpolation
        3.  degrades resized crop with degradation_fn

        :param size: resizing to size after cropping
        :param degradation: degradation_fn, e.g. cv_bicubic or bsrgan_light
        :param downscale_f: Low Resolution Downsample factor
        :param min_crop_f: determines crop size s,
          where s = c * min_img_side_len with c sampled from interval (min_crop_f, max_crop_f)
        :param max_crop_f: ""
        :param data_root:
        :param random_crop:
        """
        self.base = self.get_base()
        assert size
        assert (size / downscale_f).is_integer()
        self.size = size
        self.LR_size = int(size / downscale_f)
        self.min_crop_f = min_crop_f
        self.max_crop_f = max_crop_f
        assert(max_crop_f <= 1.)
        self.center_crop = not random_crop

        self.image_rescaler = albumentations.SmallestMaxSize(max_size=size, interpolation=cv2.INTER_AREA)

        self.pil_interpolation = False # gets reset later if incase interp_op is from pillow

        if degradation == "bsrgan":
            self.degradation_process = partial(degradation_fn_bsr, sf=downscale_f)

        elif degradation == "bsrgan_light":
            self.degradation_process = partial(degradation_fn_bsr_light, sf=downscale_f)

        else:
            interpolation_fn = {
            "cv_nearest": cv2.INTER_NEAREST,
            "cv_bilinear": cv2.INTER_LINEAR,
            "cv_bicubic": cv2.INTER_CUBIC,
            "cv_area": cv2.INTER_AREA,
            "cv_lanczos": cv2.INTER_LANCZOS4,
            "pil_nearest": PIL.Image.NEAREST,
            "pil_bilinear": PIL.Image.BILINEAR,
            "pil_bicubic": PIL.Image.BICUBIC,
            "pil_box": PIL.Image.BOX,
            "pil_hamming": PIL.Image.HAMMING,
            "pil_lanczos": PIL.Image.LANCZOS,
            }[degradation]

            self.pil_interpolation = degradation.startswith("pil_")

            if self.pil_interpolation:
                self.degradation_process = partial(TF.resize, size=self.LR_size, interpolation=interpolation_fn)

            else:
                self.degradation_process = albumentations.SmallestMaxSize(max_size=self.LR_size,
                                                                          interpolation=interpolation_fn)

    def __len__(self):
        return len(self.base)

    def __getitem__(self, i):
        example = self.base[i]
        image = Image.open(example["file_path_"])

        if not image.mode == "RGB":
            image = image.convert("RGB")

        image = np.array(image).astype(np.uint8)

        min_side_len = min(image.shape[:2])
        crop_side_len = min_side_len * np.random.uniform(self.min_crop_f, self.max_crop_f, size=None)
        crop_side_len = int(crop_side_len)

        if self.center_crop:
            self.cropper = albumentations.CenterCrop(height=crop_side_len, width=crop_side_len)

        else:
            self.cropper = albumentations.RandomCrop(height=crop_side_len, width=crop_side_len)

        image = self.cropper(image=image)["image"]
        image = self.image_rescaler(image=image)["image"]

        if self.pil_interpolation:
            image_pil = PIL.Image.fromarray(image)
            LR_image = self.degradation_process(image_pil)
            LR_image = np.array(LR_image).astype(np.uint8)

        else:
            LR_image = self.degradation_process(image=image)["image"]

        example["image"] = (image/127.5 - 1.0).astype(np.float32)
        example["LR_image"] = (LR_image/127.5 - 1.0).astype(np.float32)
        example["caption"] = example["human_label"]  # dummy caption
        return example


class ImageNetSRTrain(ImageNetSR):
    def __init__(self, **kwargs):
        super().__init__(**kwargs)

    def get_base(self):
        with open("data/imagenet_train_hr_indices.p", "rb") as f:
            indices = pickle.load(f)
        dset = ImageNetTrain(process_images=False,)
        return Subset(dset, indices)


class ImageNetSRValidation(ImageNetSR):
    def __init__(self, **kwargs):
        super().__init__(**kwargs)

    def get_base(self):
        with open("data/imagenet_val_hr_indices.p", "rb") as f:
            indices = pickle.load(f)
        dset = ImageNetValidation(process_images=False,)
        return Subset(dset, indices)