| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122 |
- Global:
- model_name: PP-FormulaNet_plus-L # To use static model for inference.
- use_gpu: True
- epoch_num: 10
- log_smooth_window: 10
- print_batch_step: 10
- save_model_dir: ./output/rec/pp_formulanet_plus_l/
- save_epoch_step: 2
- # evaluation is run every 417 iterations (1 epoch)(batch_size = 24) # max_seq_len: 1024
- eval_batch_step: [0, 417 ]
- cal_metric_during_train: True
- pretrained_model:
- checkpoints:
- save_inference_dir:
- use_visualdl: False
- infer_img: doc/datasets/pme_demo/0000013.png
- infer_mode: False
- use_space_char: False
- rec_char_dict_path: &rec_char_dict_path ppocr/utils/dict/unimernet_tokenizer
- max_new_tokens: &max_new_tokens 2560
- input_size: &input_size [768, 768]
- save_res_path: ./output/rec/predicts_pp_formulanet_plus_l.txt
- allow_resize_largeImg: False
- start_ema: True
- d2s_train_image_shape: [1,768,768]
- Optimizer:
- name: AdamW
- beta1: 0.9
- beta2: 0.999
- weight_decay: 0.05
- lr:
- name: LinearWarmupCosine
- learning_rate: 0.0001
- Architecture:
- model_type: rec
- algorithm: PP-FormulaNet_plus-L
- in_channels: 3
- Transform:
- Backbone:
- name: Vary_VIT_B_Formula
- image_size: 768
- encoder_embed_dim: 768
- encoder_depth: 12
- encoder_num_heads: 12
- encoder_global_attn_indexes: [2, 5, 8, 11]
- Head:
- name: PPFormulaNet_Head
- max_new_tokens: *max_new_tokens
- decoder_start_token_id: 0
- decoder_ffn_dim: 2048
- decoder_hidden_size: 512
- decoder_layers: 8
- temperature: 0.2
- do_sample: False
- top_p: 0.95
- encoder_hidden_size: 1024
- is_export: False
- length_aware: False
- use_parallel: False
- parallel_step: 0
- Loss:
- name: PPFormulaNet_L_Loss
- PostProcess:
- name: UniMERNetDecode
- rec_char_dict_path: *rec_char_dict_path
- Metric:
- name: LaTeXOCRMetric
- main_indicator: exp_rate
- cal_bleu_score: True
- Train:
- dataset:
- name: SimpleDataSet
- data_dir: ./ocr_rec_latexocr_dataset_example
- label_file_list: ["./ocr_rec_latexocr_dataset_example/train.txt"]
- transforms:
- - UniMERNetImgDecode:
- input_size: *input_size
- random_padding: True
- random_resize: True
- random_crop: True
- - UniMERNetTrainTransform:
- - LatexImageFormat:
- - UniMERNetLabelEncode:
- rec_char_dict_path: *rec_char_dict_path
- max_seq_len: *max_new_tokens
- - KeepKeys:
- keep_keys: ['image', 'label', 'attention_mask']
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 3
- num_workers: 0
- collate_fn: UniMERNetCollator
- Eval:
- dataset:
- name: SimpleDataSet
- data_dir: ./ocr_rec_latexocr_dataset_example
- label_file_list: ["./ocr_rec_latexocr_dataset_example/val.txt"]
- transforms:
- - UniMERNetImgDecode:
- input_size: *input_size
- - UniMERNetTestTransform:
- - LatexImageFormat:
- - UniMERNetLabelEncode:
- max_seq_len: *max_new_tokens
- rec_char_dict_path: *rec_char_dict_path
- - KeepKeys:
- keep_keys: ['image', 'label', 'attention_mask', 'filename']
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 10
- num_workers: 0
- collate_fn: UniMERNetCollator
|
