ldm/modules/losses_audio/vggishish/configs/vggish.yaml

seed: 1337
log_code_state: True
# patterns to ignore when backing up the code folder
patterns_to_ignore: ['logs', '.git', '__pycache__']

# data:
mels_path: '/home/nvme/data/vggsound/features/melspec_10s_22050hz/'
spec_shape: [80, 860]
cropped_size: [80, 848]
random_crop: False

# model:
# original vgg family except for MP is missing at the end
# 'vggish': [64, 'MP', 128, 'MP', 256, 256, 'MP', 512, 512]
# 'vgg11': [64, 'MP', 128, 'MP', 256, 256, 'MP', 512, 512, 'MP', 512, 512],
# 'vgg13': [64, 64, 'MP', 128, 128, 'MP', 256, 256, 'MP', 512, 512, 'MP', 512, 512],
# 'vgg16': [64, 64, 'MP', 128, 128, 'MP', 256, 256, 256, 'MP', 512, 512, 512, 'MP', 512, 512, 512],
# 'vgg19': [64, 64, 'MP', 128, 128, 'MP', 256, 256, 256, 256, 'MP', 512, 512, 512, 512, 'MP', 512, 512, 512, 512],
conv_layers: [64, 64, 'MP', 128, 128, 'MP', 256, 256, 256, 'MP', 512, 512, 512, 'MP', 512, 512, 512]
use_bn: False

# train:
device: 'cuda:0'
batch_size: 32
num_workers: 0
optimizer: adam
betas: [0.9, 0.999]
momentum: 0.9
learning_rate: 3e-4
weight_decay: 0.0001
num_epochs: 100
patience: 3
logdir: './logs'
cls_weights_in_loss: False