PAVAS/configs/data/base.yaml at main · SonyResearch/PAVAS · GitHub

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
finetune:
  enabled: true
  split: train

VGGSound:
  root: /path/to/vggsound/video
  subset_name: sets/vgg3-train.tsv
  fps: 8
  height: 384
  width: 384
  sample_duration_sec: 8.0

VGGSound_test:
  root: /path/to/vggsound/video
  subset_name: sets/vgg3-test.tsv
  fps: 8
  height: 384
  width: 384
  sample_duration_sec: 8.0

VGGSound_val:
  root: /path/to/vggsound/video
  subset_name: sets/vgg3-val.tsv
  fps: 8
  height: 384
  width: 384
  sample_duration_sec: 8.0

ExtractedVGG:
  tag: train
  tsv: /path/to/mmaudio_cache/vgg-train.tsv
  memmap_dir: /path/to/mmaudio_cache/vgg-train
  object_cond:
    enabled: true
    enable_patch_attn: true
    mass_root: /path/to/ppe/mass
    velocity_root: /path/to/ppe/velocity
    seg_root: /path/to/ppe/segmentation
    skip_no_prompt: true
  clip_patches:
    tsv: /path/to/clip_patches/train/vgg-patches.tsv
    npy: /path/to/clip_patches/train/vgg-patches/clip_patches.npy
    cache_items: 128

ExtractedVGG_test:
  tag: test
  gt_cache: /path/to/av_benchmark_cache/vggsound-test
  output_subdir: null
  tsv: /path/to/mmaudio_cache/vgg-test.tsv
  memmap_dir: /path/to/mmaudio_cache/vgg-test
  object_cond:
    enabled: true
    enable_patch_attn: true
    mass_root: /path/to/ppe/mass
    velocity_root: /path/to/ppe/velocity
    seg_root: /path/to/ppe/segmentation
    skip_no_prompt: true
  clip_patches:
    tsv: /path/to/clip_patches/test/vgg-patches.tsv
    npy: /path/to/clip_patches/test/vgg-patches/clip_patches.npy
    cache_items: 128

ExtractedVGG_val:
  tag: val
  gt_cache: /path/to/av_benchmark_cache/vggsound-val
  output_subdir: val
  tsv: /path/to/mmaudio_cache/vgg-val.tsv
  memmap_dir: /path/to/mmaudio_cache/vgg-val
  object_cond:
    enabled: true
    enable_patch_attn: true
    mass_root: /path/to/ppe/mass
    velocity_root: /path/to/ppe/velocity
    seg_root: /path/to/ppe/segmentation
    skip_no_prompt: true
  clip_patches:
    tsv: /path/to/clip_patches/val/vgg-patches.tsv
    npy: /path/to/clip_patches/val/vgg-patches/clip_patches.npy
    cache_items: 128

AudioCaps:
  tsv: /path/to/mmaudio_cache/audiocaps.tsv
  memmap_dir: /path/to/mmaudio_cache/audiocaps

AudioSetSL:
  tsv: /path/to/mmaudio_cache/audioset_sl.tsv
  memmap_dir: /path/to/mmaudio_cache/audioset_sl

BBCSound:
  tsv: /path/to/mmaudio_cache/bbcsound.tsv
  memmap_dir: /path/to/mmaudio_cache/bbcsound

FreeSound:
  tsv: /path/to/mmaudio_cache/freesound.tsv
  memmap_dir: /path/to/mmaudio_cache/freesound

Clotho:
  tsv: /path/to/mmaudio_cache/clotho.tsv
  memmap_dir: /path/to/mmaudio_cache/clotho

Example_video:
  tsv: ./training/example_output/memmap/vgg-example.tsv
  memmap_dir: ./training/example_output/memmap/vgg-example

Example_audio:
  tsv: ./training/example_output/memmap/audio-example.tsv
  memmap_dir: ./training/example_output/memmap/audio-example