File size: 1,773 Bytes
a92ae91 |
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 |
_base_ = [
'../../_base_/default_runtime.py',
'../../_base_/recog_pipelines/satrn_pipeline.py',
'../../_base_/recog_datasets/ST_MJ_train.py',
'../../_base_/recog_datasets/academic_test.py'
]
train_list = {{_base_.train_list}}
test_list = {{_base_.test_list}}
train_pipeline = {{_base_.train_pipeline}}
test_pipeline = {{_base_.test_pipeline}}
label_convertor = dict(
type='AttnConvertor', dict_type='DICT90', with_unknown=True)
model = dict(
type='SATRN',
backbone=dict(type='ShallowCNN', input_channels=3, hidden_dim=512),
encoder=dict(
type='SatrnEncoder',
n_layers=12,
n_head=8,
d_k=512 // 8,
d_v=512 // 8,
d_model=512,
n_position=100,
d_inner=512 * 4,
dropout=0.1),
decoder=dict(
type='NRTRDecoder',
n_layers=6,
d_embedding=512,
n_head=8,
d_model=512,
d_inner=512 * 4,
d_k=512 // 8,
d_v=512 // 8),
loss=dict(type='TFLoss'),
label_convertor=label_convertor,
max_seq_len=25)
# optimizer
optimizer = dict(type='Adam', lr=3e-4)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(policy='step', step=[3, 4])
total_epochs = 6
data = dict(
samples_per_gpu=64,
workers_per_gpu=4,
val_dataloader=dict(samples_per_gpu=1),
test_dataloader=dict(samples_per_gpu=1),
train=dict(
type='UniformConcatDataset',
datasets=train_list,
pipeline=train_pipeline),
val=dict(
type='UniformConcatDataset',
datasets=test_list,
pipeline=test_pipeline),
test=dict(
type='UniformConcatDataset',
datasets=test_list,
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='acc')
|