add ppocrv3 rec (PaddlePaddle#6033)

* add ppocrv3 rec

configs/rec/ch_PP-OCRv3/ch_PP-OCRv3_rec.yml

@@ -0,0 +1,131 @@
+Global:
+ debug: false
+ use_gpu: true
+ epoch_num: 500
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_ppocr_v3
+ save_epoch_step: 3
+ eval_batch_step: [0, 2000]
+ cal_metric_during_train: true
+ pretrained_model:
+ checkpoints:
+ save_inference_dir:
+ use_visualdl: false
+ infer_img: doc/imgs_words/ch/word_1.jpg
+ character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+ max_text_length: &max_text_length 25
+ infer_mode: false
+ use_space_char: true
+ distributed: true
+ save_res_path: ./output/rec/predicts_ppocrv3.txt
+
+
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Cosine
+ learning_rate: 0.001
+ warmup_epoch: 5
+ regularizer:
+ name: L2
+ factor: 3.0e-05
+
+
+Architecture:
+ model_type: rec
+ algorithm: SVTR
+ Transform:
+ Backbone:
+ name: MobileNetV1Enhance
+ scale: 0.5
+ last_conv_stride: [1, 2]
+ last_pool_type: avg
+ Head:
+ name: MultiHead
+ head_list:
+ - CTCHead:
+ Neck:
+ name: svtr
+ dims: 64
+ depth: 2
+ hidden_dims: 120
+ use_guide: True
+ Head:
+ fc_decay: 0.00001
+ - SARHead:
+ enc_dim: 512
+ max_text_length: *max_text_length
+
+Loss:
+ name: MultiLoss
+ loss_config_list:
+ - CTCLoss:
+ - SARLoss:
+
+PostProcess: 
+ name: CTCLabelDecode
+
+Metric:
+ name: RecMetric
+ main_indicator: acc
+ ignore_space: True
+
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: ./train_data/
+ ext_op_transform_idx: 1
+ label_file_list:
+ - ./train_data/train_list.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecConAug:
+ prob: 0.5
+ ext_data_num: 2
+ image_shape: [48, 320, 3]
+ - RecAug:
+ - MultiLabelEncode:
+ - RecResizeImg:
+ image_shape: [3, 48, 320]
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label_ctc
+ - label_sar
+ - length
+ - valid_ratio
+ loader:
+ shuffle: true
+ batch_size_per_card: 128
+ drop_last: true
+ num_workers: 4
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: ./train_data
+ label_file_list:
+ - ./train_data/val_list.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - MultiLabelEncode:
+ - RecResizeImg:
+ image_shape: [3, 48, 320]
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label_ctc
+ - label_sar
+ - length
+ - valid_ratio
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 128
+ num_workers: 4

configs/rec/ch_PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml

@@ -0,0 +1,205 @@
+Global:
+ debug: false
+ use_gpu: true
+ epoch_num: 800
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_ppocr_v3_distillation
+ save_epoch_step: 3
+ eval_batch_step: [0, 2000]
+ cal_metric_during_train: true
+ pretrained_model:
+ checkpoints:
+ save_inference_dir:
+ use_visualdl: false
+ infer_img: doc/imgs_words/ch/word_1.jpg
+ character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+ max_text_length: &max_text_length 25
+ infer_mode: false
+ use_space_char: true
+ distributed: true
+ save_res_path: ./output/rec/predicts_ppocrv3_distillation.txt
+
+
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Piecewise
+ decay_epochs : [700, 800]
+ values : [0.0005, 0.00005]
+ warmup_epoch: 5
+ regularizer:
+ name: L2
+ factor: 3.0e-05
+
+
+Architecture:
+ model_type: &model_type "rec"
+ name: DistillationModel
+ algorithm: Distillation
+ Models:
+ Teacher:
+ pretrained:
+ freeze_params: false
+ return_all_feats: true
+ model_type: *model_type
+ algorithm: SVTR
+ Transform:
+ Backbone:
+ name: MobileNetV1Enhance
+ scale: 0.5
+ last_conv_stride: [1, 2]
+ last_pool_type: avg
+ Head:
+ name: MultiHead
+ head_list:
+ - CTCHead:
+ Neck:
+ name: svtr
+ dims: 64
+ depth: 2
+ hidden_dims: 120
+ use_guide: True
+ Head:
+ fc_decay: 0.00001
+ - SARHead:
+ enc_dim: 512
+ max_text_length: *max_text_length
+ Student:
+ pretrained:
+ freeze_params: false
+ return_all_feats: true
+ model_type: *model_type
+ algorithm: SVTR
+ Transform:
+ Backbone:
+ name: MobileNetV1Enhance
+ scale: 0.5
+ last_conv_stride: [1, 2]
+ last_pool_type: avg
+ Head:
+ name: MultiHead
+ head_list:
+ - CTCHead:
+ Neck:
+ name: svtr
+ dims: 64
+ depth: 2
+ hidden_dims: 120
+ use_guide: True
+ Head:
+ fc_decay: 0.00001
+ - SARHead:
+ enc_dim: 512
+ max_text_length: *max_text_length
+Loss:
+ name: CombinedLoss
+ loss_config_list:
+ - DistillationDMLLoss:
+ weight: 1.0
+ act: "softmax"
+ use_log: true
+ model_name_pairs:
+ - ["Student", "Teacher"]
+ key: head_out
+ multi_head: True
+ dis_head: ctc
+ name: dml_ctc
+ - DistillationDMLLoss:
+ weight: 0.5
+ act: "softmax"
+ use_log: true
+ model_name_pairs:
+ - ["Student", "Teacher"]
+ key: head_out
+ multi_head: True
+ dis_head: sar
+ name: dml_sar
+ - DistillationDistanceLoss:
+ weight: 1.0
+ mode: "l2"
+ model_name_pairs:
+ - ["Student", "Teacher"]
+ key: backbone_out
+ - DistillationCTCLoss:
+ weight: 1.0
+ model_name_list: ["Student", "Teacher"]
+ key: head_out
+ multi_head: True
+ - DistillationSARLoss:
+ weight: 1.0
+ model_name_list: ["Student", "Teacher"]
+ key: head_out
+ multi_head: True
+
+PostProcess:
+ name: DistillationCTCLabelDecode
+ model_name: ["Student", "Teacher"]
+ key: head_out
+ multi_head: True
+
+Metric:
+ name: DistillationMetric
+ base_metric_name: RecMetric
+ main_indicator: acc
+ key: "Student"
+ ignore_space: True
+
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: ./train_data/
+ ext_op_transform_idx: 1
+ label_file_list:
+ - ./train_data/train_list.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecConAug:
+ prob: 0.5
+ ext_data_num: 2
+ image_shape: [48, 320, 3]
+ - RecAug:
+ - MultiLabelEncode:
+ - RecResizeImg:
+ image_shape: [3, 48, 320]
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label_ctc
+ - label_sar
+ - length
+ - valid_ratio
+ loader:
+ shuffle: true
+ batch_size_per_card: 128
+ drop_last: true
+ num_workers: 4
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: ./train_data
+ label_file_list:
+ - ./train_data/val_list.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - MultiLabelEncode:
+ - RecResizeImg:
+ image_shape: [3, 48, 320]
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label_ctc
+ - label_sar
+ - length
+ - valid_ratio
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 128
+ num_workers: 4

ppocr/data/imaug/__init__.py

@@ -22,7 +22,7 @@
 from .random_crop_data import EastRandomCropData, RandomCropImgMask
 from .make_pse_gt import MakePseGt
 
-from .rec_img_aug import RecAug, RecResizeImg, ClsResizeImg, \
+from .rec_img_aug import RecAug, RecConAug, RecResizeImg, ClsResizeImg, \
  SRNRecResizeImg, NRTRRecResizeImg, SARRecResizeImg, PRENResizeImg
 from .randaugment import RandAugment
 from .copy_paste import CopyPaste

ppocr/data/imaug/label_ops.py

@@ -22,6 +22,7 @@
 import string
 from shapely.geometry import LineString, Point, Polygon
 import json
+import copy
 
 from ppocr.utils.logging import get_logger
 
@@ -1007,3 +1008,34 @@ def _parse_label(self, label, encode_res):
  gt_label.extend([self.label2id_map[("i-" + label).upper()]] *
  (len(encode_res["input_ids"]) - 1))
  return gt_label
+
+
+class MultiLabelEncode(BaseRecLabelEncode):
+ def __init__(self,
+ max_text_length,
+ character_dict_path=None,
+ use_space_char=False,
+ **kwargs):
+ super(MultiLabelEncode, self).__init__(
+ max_text_length, character_dict_path, use_space_char)
+
+ self.ctc_encode = CTCLabelEncode(max_text_length, character_dict_path,
+ use_space_char, **kwargs)
+ self.sar_encode = SARLabelEncode(max_text_length, character_dict_path,
+ use_space_char, **kwargs)
+
+ def __call__(self, data):
+
+ data_ctc = copy.deepcopy(data)
+ data_sar = copy.deepcopy(data)
+ data_out = dict()
+ data_out['img_path'] = data.get('img_path', None)
+ data_out['image'] = data['image']
+ ctc = self.ctc_encode.__call__(data_ctc)
+ sar = self.sar_encode.__call__(data_sar)
+ if ctc is None or sar is None:
+ return None
+ data_out['label_ctc'] = ctc['label']
+ data_out['label_sar'] = sar['label']
+ data_out['length'] = ctc['length']
+ return data_out