版本信息：
python 3.8.8
paddle 2.2.1
cuda 11.6
cudnn 8.2.1
release 2.5

配置：
batch_size_per_card: 1
num_workers: 1

问题：loss不下降了

补充说明：从lr=0.001开始训练，loss下降到6左右不下降了，下调lr也没有怎么下降，acc始终是0

配置文件其他信息如下：
Global:
use_gpu: true
epoch_num: 400
log_smooth_window: 20
print_batch_step: 5
save_model_dir: ./output/table_mv3/
save_epoch_step: 3

evaluation is run every 400 iterations after the 0th iteration

eval_batch_step: [0, 400]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/table/table.jpg

for data or label process

character_dict_path: ppocr/utils/dict/table_structure_dict.txt
character_type: en
max_text_length: 100
max_elem_length: 800
max_cell_num: 500
infer_mode: False
process_total_num: 0
process_cut_num: 0

Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
clip_norm: 5.0
lr:
#learning_rate: 0.001
learning_rate: 0.000005
regularizer:
name: 'L2'
factor: 0.00000

Architecture:
model_type: table
algorithm: TableAttn
Backbone:
name: MobileNetV3
scale: 1.0
model_name: large
Head:
name: TableAttentionHead
hidden_size: 256
l2_decay: 0.00001
loc_type: 2
max_text_length: 100
max_elem_length: 800
max_cell_num: 500

Loss:
name: TableAttentionLoss
structure_weight: 100.0
loc_weight: 10000.0

PostProcess:
name: TableLabelDecode

Metric:
name: TableMetric
main_indicator: acc

Train:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/train/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_train.jsonl
transforms:

• DecodeImage: # load image
  img_mode: BGR
  channel_first: False
• ResizeTableImage:
  max_len: 488
• TableLabelEncode:
• NormalizeImage:
  scale: 1./255.
  mean: [0.485, 0.456, 0.406]
  std: [0.229, 0.224, 0.225]
  order: 'hwc'
• PaddingTableImage:
• ToCHWImage:
• KeepKeys:
  keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
  loader:
  shuffle: True
  batch_size_per_card: 1
  #batch_size_per_card: 32
  drop_last: True
  num_workers: 1

Eval:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/val/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl
transforms:

• DecodeImage: # load image
  img_mode: BGR
  channel_first: False
• ResizeTableImage:
  max_len: 488
• TableLabelEncode:
• NormalizeImage:
  scale: 1./255.
  mean: [0.485, 0.456, 0.406]
  std: [0.229, 0.224, 0.225]
  order: 'hwc'
• PaddingTableImage:
• ToCHWImage:
• KeepKeys:
  keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
  loader:
  shuffle: False
  drop_last: False
  batch_size_per_card: 1
  num_workers: 1