ABINet-OCR / configs /train_abinet_sv.yaml
tomofi's picture
Add application file
cb433d6
global:
name: train-abinet-sv
phase: train
stage: train-super
workdir: workdir
seed: ~
dataset:
train: {
roots: ['data/training/MJ/MJ_train/',
'data/training/MJ/MJ_test/',
'data/training/MJ/MJ_valid/',
'data/training/ST'],
batch_size: 384
}
test: {
roots: ['data/evaluation/IIIT5k_3000',
'data/evaluation/SVT',
'data/evaluation/SVTP',
'data/evaluation/IC13_857',
'data/evaluation/IC15_1811',
'data/evaluation/CUTE80'],
batch_size: 384
}
data_aug: True
multiscales: False
num_workers: 14
training:
epochs: 10
show_iters: 50
eval_iters: 3000
save_iters: 3000
optimizer:
type: Adam
true_wd: False
wd: 0.0
bn_wd: False
clip_grad: 20
lr: 0.0001
args: {
betas: !!python/tuple [0.9, 0.999], # for default Adam
}
scheduler: {
periods: [6, 4],
gamma: 0.1,
}
model:
name: 'modules.model_abinet_iter.ABINetIterModel'
iter_size: 3
ensemble: ''
use_vision: False
vision: {
checkpoint: workdir/pretrain-vision-model-sv/best-pretrain-vision-model-sv.pth,
loss_weight: 1.,
attention: 'attention',
backbone: 'transformer',
backbone_ln: 2,
}
language: {
checkpoint: workdir/pretrain-language-model/pretrain-language-model.pth,
num_layers: 4,
loss_weight: 1.,
detach: True,
use_self_attn: False
}
alignment: {
loss_weight: 1.,
}