openocr-python 0.0.2__py3-none-any.whl

openocr/configs/rec/svtrv2/svtrv2_small_rctc.yml

@@ -0,0 +1,135 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/svtrv2_small_rctc/
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_epoch_step: [0, 1]
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt
+  max_text_length: &max_text_length 25
+  use_space_char: &use_space_char False
+  save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_rctc.txt
+  use_amp: True
+
+Optimizer:
+  name: AdamW
+  lr: 0.00065 # for 4gpus bs256/gpu
+  weight_decay: 0.05
+  filter_bias_and_bn: True
+
+LRScheduler:
+  name: OneCycleLR
+  warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
+  cycle_momentum: False
+
+Architecture:
+  model_type: rec
+  algorithm: SVTRv2
+  Transform:
+  Encoder:
+    name: SVTRv2LNConvTwo33
+    use_pos_embed: False
+    dims: [96, 192, 384]
+    depths: [3, 6, 3]
+    num_heads: [3, 6, 12]
+    mixer: [['Conv','Conv','Conv'],['Conv','Conv','Conv','FGlobal','Global','Global'],['Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[1, 1], [2, 1], [-1, -1]]
+    last_stage: false
+    feat2d: True
+  Decoder:
+    name: RCTCDecoder
+
+Loss:
+  name: CTCLoss
+  zero_infinity: True
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: ['../Union14M-L-LMDB-Filtered/filter_train_challenging',
+    '../Union14M-L-LMDB-Filtered/filter_train_hard',
+    '../Union14M-L-LMDB-Filtered/filter_train_medium',
+    '../Union14M-L-LMDB-Filtered/filter_train_normal',
+    '../Union14M-L-LMDB-Filtered/filter_train_easy',
+    ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - PARSeqAugPIL:
+      - CTCLabelEncode: # Class handling label
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length']
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: &bs 256
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: True
+    batch_size_per_card: *bs
+    drop_last: True
+    max_ratio: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: [
+      '../evaluation/CUTE80',
+      '../evaluation/IC13_857',
+      '../evaluation/IC15_1811',
+      '../evaluation/IIIT5k',
+      '../evaluation/SVT',
+      '../evaluation/SVTP',
+      ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - CTCLabelEncode: # Class handling label
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length']
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: 256
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: False
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: *bs
+    max_ratio: 4
+    num_workers: 4

openocr/configs/rec/svtrv2/svtrv2_smtr_gtc_rctc.yml

@@ -0,0 +1,162 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/svtrv2_smtr_gtc_rctc_maxratio12
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 500]
+  eval_epoch_step: [0, 1]
+  cal_metric_during_train: True
+  pretrained_model:
+  # ./output/rec/u14m_filter/svtrv2_rctc/best.pth
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt # 96en
+  # ./tools/utils/ppocr_keys_v1.txt  # ch
+  max_text_length: &max_text_length 25
+  use_space_char: &use_space_char False
+  save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_smtr_gtc_rctc.txt
+  use_amp: True
+
+Optimizer:
+  name: AdamW
+  lr: 0.000325 # for 4gpus bs128/gpu
+  weight_decay: 0.05
+  filter_bias_and_bn: True
+
+LRScheduler:
+  name: OneCycleLR
+  warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
+  cycle_momentum: False
+
+Architecture:
+  model_type: rec
+  algorithm: SVTRv2
+  in_channels: 3
+  Transform:
+  Encoder:
+    name: SVTRv2LNConvTwo33
+    use_pos_embed: False
+    dims: [128, 256, 384]
+    depths: [6, 6, 6]
+    num_heads: [4, 8, 12]
+    mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','FGlobal','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[1, 1], [2, 1], [-1, -1]]
+    last_stage: false
+    feat2d: True
+  Decoder:
+    name: GTCDecoder
+    infer_gtc: True
+    detach: False
+    gtc_decoder:
+      name: SMTRDecoder
+      num_layer: 1
+      ds: True
+      max_len: *max_text_length
+      next_mode: &next True
+      sub_str_len: &subsl 5
+    ctc_decoder:
+      name: RCTCDecoder
+
+Loss:
+  name: GTCLoss
+  ctc_weight: 0.1
+  gtc_loss:
+    name: SMTRLoss
+
+PostProcess:
+  name: GTCLabelDecode
+  gtc_label_decode:
+    name: SMTRLabelDecode
+    next_mode: *next
+  character_dict_path: *character_dict_path
+  use_space_char: *use_space_char
+
+Metric:
+  name: RecGTCMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: false
+    data_dir_list: ['../Union14M-L-LMDB-Filtered/filter_train_challenging',
+    '../Union14M-L-LMDB-Filtered/filter_train_hard',
+    '../Union14M-L-LMDB-Filtered/filter_train_medium',
+    '../Union14M-L-LMDB-Filtered/filter_train_normal',
+    '../Union14M-L-LMDB-Filtered/filter_train_easy',
+    ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - PARSeqAugPIL:
+      - GTCLabelEncode: # Class handling label
+          gtc_label_encode:
+            name: SMTRLabelEncode
+            sub_str_len: *subsl
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'label_subs', 'label_next', 'length_subs',
+          'label_subs_pre', 'label_next_pre', 'length_subs_pre', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: &bs 128
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: True
+    batch_size_per_card: *bs
+    drop_last: True
+    max_ratio: &max_ratio 12
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: [
+      '../evaluation/CUTE80',
+      '../evaluation/IC13_857',
+      '../evaluation/IC15_1811',
+      '../evaluation/IIIT5k',
+      '../evaluation/SVT',
+      '../evaluation/SVTP',
+      ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - GTCLabelEncode: # Class handling label
+          gtc_label_encode:
+            name: ARLabelEncode
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: *bs
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: False
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: *bs
+    max_ratio: *max_ratio
+    num_workers: 4

openocr/configs/rec/svtrv2/svtrv2_smtr_gtc_rctc_ch.yml

@@ -0,0 +1,153 @@
+Global:
+  device: gpu
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/ch/svtrv2_smtr_gtc_rctc_ch
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  eval_epoch_step: [0, 1]
+  cal_metric_during_train: False
+  pretrained_model:
+  # ./output/rec/u14m_filter/svtrv2_rctc/best.pth
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: &character_dict_path ./tools/utils/ppocr_keys_v1.txt # ch
+  max_text_length: &max_text_length 25
+  use_space_char: &use_space_char False
+  save_res_path: ./output/rec/ch/predicts_svtrv2_smtr_gtc_rctc_ch.txt
+  use_amp: True
+
+Optimizer:
+  name: AdamW
+  lr: 0.00065 # for 4gpus bs256/gpu
+  weight_decay: 0.05
+  filter_bias_and_bn: True
+
+LRScheduler:
+  name: OneCycleLR
+  warmup_epoch: 5
+  cycle_momentum: False
+
+Architecture:
+  model_type: rec
+  algorithm: SVTRv2
+  in_channels: 3
+  Transform:
+  Encoder:
+    name: SVTRv2LNConvTwo33
+    use_pos_embed: False
+    dims: [128, 256, 384]
+    depths: [6, 6, 6]
+    num_heads: [4, 8, 12]
+    mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','FGlobal','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[1, 1], [2, 1], [-1, -1]]
+    last_stage: false
+    feat2d: True
+  Decoder:
+    name: GTCDecoder
+    infer_gtc: True
+    detach: False
+    gtc_decoder:
+      name: SMTRDecoder
+      num_layer: 1
+      ds: True
+      max_len: *max_text_length
+      next_mode: &next True
+      sub_str_len: &subsl 5
+    ctc_decoder:
+      name: RCTCDecoder
+
+Loss:
+  name: GTCLoss
+  ctc_weight: 0.1
+  gtc_loss:
+    name: SMTRLoss
+
+PostProcess:
+  name: GTCLabelDecode
+  gtc_label_decode:
+    name: SMTRLabelDecode
+    next_mode: *next
+  character_dict_path: *character_dict_path
+  use_space_char: *use_space_char
+
+Metric:
+  name: RecGTCMetric
+  main_indicator: acc
+  # is_filter: True
+
+Train:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: false
+    data_dir_list: ['../benchmark_bctr/benchmark_bctr_train/document_train',
+    '../benchmark_bctr/benchmark_bctr_train/handwriting_train',
+    '../benchmark_bctr/benchmark_bctr_train/scene_train',
+    '../benchmark_bctr/benchmark_bctr_train/web_train'
+    ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - PARSeqAugPIL:
+      - GTCLabelEncode: # Class handling label
+          gtc_label_encode:
+            name: SMTRLabelEncode
+            sub_str_len: *subsl
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'label_subs', 'label_next', 'length_subs',
+          'label_subs_pre', 'label_next_pre', 'length_subs_pre', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: &bs 256
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: True
+    batch_size_per_card: *bs
+    drop_last: True
+    max_ratio: &max_ratio 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: ['../benchmark_bctr/benchmark_bctr_test/scene_test']
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - GTCLabelEncode: # Class handling label
+          gtc_label_encode:
+            name: ARLabelEncode
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: *bs
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: False
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: *bs
+    max_ratio: *max_ratio
+    num_workers: 4

openocr/configs/rec/svtrv2/svtrv2_tiny_rctc.yml

@@ -0,0 +1,135 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/svtrv2_tiny_rctc/
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_epoch_step: [0, 1]
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt
+  max_text_length: &max_text_length 25
+  use_space_char: &use_space_char False
+  save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_rctc.txt
+  use_amp: True
+
+Optimizer:
+  name: AdamW
+  lr: 0.00065 # for 4gpus bs256/gpu
+  weight_decay: 0.05
+  filter_bias_and_bn: True
+
+LRScheduler:
+  name: OneCycleLR
+  warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
+  cycle_momentum: False
+
+Architecture:
+  model_type: rec
+  algorithm: SVTRv2
+  Transform:
+  Encoder:
+    name: SVTRv2LNConvTwo33
+    use_pos_embed: False
+    dims: [64, 128, 256]
+    depths: [3, 6, 3]
+    num_heads: [2, 4, 8]
+    mixer: [['Conv','Conv','Conv'],['Conv','Conv','Conv','FGlobal','Global','Global'],['Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[1, 1], [2, 1], [-1, -1]]
+    last_stage: false
+    feat2d: True
+  Decoder:
+    name: RCTCDecoder
+
+Loss:
+  name: CTCLoss
+  zero_infinity: True
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: ['../Union14M-L-LMDB-Filtered/filter_train_challenging',
+    '../Union14M-L-LMDB-Filtered/filter_train_hard',
+    '../Union14M-L-LMDB-Filtered/filter_train_medium',
+    '../Union14M-L-LMDB-Filtered/filter_train_normal',
+    '../Union14M-L-LMDB-Filtered/filter_train_easy',
+    ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - PARSeqAugPIL:
+      - CTCLabelEncode: # Class handling label
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length']
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: &bs 256
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: True
+    batch_size_per_card: *bs
+    drop_last: True
+    max_ratio: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: RatioDataSetTVResize
+    ds_width: True
+    padding: False
+    data_dir_list: [
+      '../evaluation/CUTE80',
+      '../evaluation/IC13_857',
+      '../evaluation/IC15_1811',
+      '../evaluation/IIIT5k',
+      '../evaluation/SVT',
+      '../evaluation/SVTP',
+      ]
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - CTCLabelEncode: # Class handling label
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length']
+  sampler:
+    name: RatioSampler
+    scales: [[128, 32]] # w, h
+    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
+    first_bs: 256
+    fix_bs: false
+    divided_factor: [4, 16] # w, h
+    is_training: False
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: *bs
+    max_ratio: 4
+    num_workers: 4

openocr/configs/rec/visionlan/resnet45_trans_visionlan_LA.yml

@@ -0,0 +1,103 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/resnet45_trans_visionlan_LA/
+  eval_epoch_step: [0, 1]
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model:
+  # ./output/rec/u14m_filter/resnet45_trans_visionlan_LF2/best.pth
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt # 96en
+  # ./tools/utils/ppocr_keys_v1.txt  # ch
+  max_text_length: &max_text_length 25
+  use_space_char: &use_space_char False
+  save_res_path: ./output/rec/u14m_filter/predicts_resnet45_trans_visionlan_LA.txt
+  grad_clip_val: 20
+  use_amp: True
+
+Optimizer:
+  name: Adam
+  lr: 0.0002 # for 4gpus bs128/gpu
+  weight_decay: 0.0
+
+LRScheduler:
+  name: MultiStepLR
+  milestones: [12]
+
+Architecture:
+  model_type: rec
+  algorithm: VisionLAN
+  Transform:
+  Encoder:
+    name: ResNet45
+    in_channels: 3
+    strides: [2, 2, 2, 1, 1]
+  Decoder:
+    name: VisionLANDecoder
+    training_step: &training_step 'LA'
+    n_position: 256
+
+Loss:
+  name: VisionLANLoss
+  training_step: *training_step
+
+PostProcess:
+  name: VisionLANLabelDecode
+  character_dict_path: *character_dict_path
+  use_space_char: *use_space_char
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ../Union14M-L-LMDB-Filtered
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - PARSeqAugPIL:
+      - VisionLANLabelEncode:
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - RecTVResize:
+          image_shape: [64, 256]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'label_res', 'label_sub', 'label_id', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 128
+    drop_last: True
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ../evaluation
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - VisionLANLabelEncode:
+          character_dict_path: *character_dict_path
+          use_space_char: *use_space_char
+          max_text_length: *max_text_length
+      - RecTVResize:
+          image_shape: [64, 256]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'label_res', 'label_sub', 'label_id', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 128
+    num_workers: 2