File size: 3,012 Bytes
45d16e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
import logging
import warnings

from video_llama.common.registry import registry
from video_llama.datasets.builders.base_dataset_builder import BaseDatasetBuilder
from video_llama.datasets.datasets.laion_dataset import LaionDataset
from video_llama.datasets.datasets.cc_sbu_dataset import CCSBUDataset, CCSBUAlignDataset


@registry.register_builder("cc_sbu")
class CCSBUBuilder(BaseDatasetBuilder):
    train_dataset_cls = CCSBUDataset

    DATASET_CONFIG_DICT = {"default": "configs/datasets/cc_sbu/defaults.yaml"}

    def _download_ann(self):
        pass

    def _download_vis(self):
        pass

    def build(self):
        self.build_processors()

        build_info = self.config.build_info

        datasets = dict()
        split = "train"

        # create datasets
        # [NOTE] return inner_datasets (wds.DataPipeline)
        dataset_cls = self.train_dataset_cls
        datasets[split] = dataset_cls(
            vis_processor=self.vis_processors[split],
            text_processor=self.text_processors[split],
            location=build_info.storage,
        ).inner_dataset

        return datasets


@registry.register_builder("laion")
class LaionBuilder(BaseDatasetBuilder):
    train_dataset_cls = LaionDataset

    DATASET_CONFIG_DICT = {"default": "configs/datasets/laion/defaults.yaml"}

    def _download_ann(self):
        pass

    def _download_vis(self):
        pass

    def build(self):
        self.build_processors()

        build_info = self.config.build_info

        datasets = dict()
        split = "train"

        # create datasets
        # [NOTE] return inner_datasets (wds.DataPipeline)
        dataset_cls = self.train_dataset_cls
        datasets[split] = dataset_cls(
            vis_processor=self.vis_processors[split],
            text_processor=self.text_processors[split],
            location=build_info.storage,
        ).inner_dataset

        return datasets


@registry.register_builder("cc_sbu_align")
class CCSBUAlignBuilder(BaseDatasetBuilder):
    train_dataset_cls = CCSBUAlignDataset

    DATASET_CONFIG_DICT = {
        "default": "configs/datasets/cc_sbu/align.yaml",
    }

    def build_datasets(self):
        # at this point, all the annotations and image/videos should be all downloaded to the specified locations.
        logging.info("Building datasets...")
        self.build_processors()

        build_info = self.config.build_info
        storage_path = build_info.storage

        datasets = dict()

        if not os.path.exists(storage_path):
            warnings.warn("storage path {} does not exist.".format(storage_path))

        # create datasets
        dataset_cls = self.train_dataset_cls
        datasets['train'] = dataset_cls(
            vis_processor=self.vis_processors["train"],
            text_processor=self.text_processors["train"],
            ann_paths=[os.path.join(storage_path, 'filter_cap.json')],
            vis_root=os.path.join(storage_path, 'image'),
        )

        return datasets