config/data/base.yaml

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

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

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

ExtractedVGG:
  tsv: ../data/v1-16-memmap/vgg-train.tsv
  memmap_dir: ../data/v1-16-memmap/vgg-train

ExtractedVGG_test:
  tag: test
  gt_cache: ../data/eval-cache/vggsound-test
  output_subdir: null
  tsv: ../data/v1-16-memmap/vgg-test.tsv
  memmap_dir: ../data/v1-16-memmap/vgg-test

ExtractedVGG_val:
  tag: val
  gt_cache: ../data/eval-cache/vggsound-val
  output_subdir: val
  tsv: ../data/v1-16-memmap/vgg-val.tsv
  memmap_dir: ../data/v1-16-memmap/vgg-val

AudioCaps:
  tsv: ../data/v1-16-memmap/audiocaps.tsv
  memmap_dir: ../data/v1-16-memmap/audiocaps

AudioSetSL:
  tsv: ../data/v1-16-memmap/audioset_sl.tsv
  memmap_dir: ../data/v1-16-memmap/audioset_sl

BBCSound:
  tsv: ../data/v1-16-memmap/bbcsound.tsv
  memmap_dir: ../data/v1-16-memmap/bbcsound

FreeSound:
  tsv: ../data/v1-16-memmap/freesound.tsv
  memmap_dir: ../data/v1-16-memmap/freesound

Clotho:
  tsv: ../data/v1-16-memmap/clotho.tsv
  memmap_dir: ../data/v1-16-memmap/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