openocr-python 0.0.2__py3-none-any.whl

openocr/__init__.py

@@ -0,0 +1,11 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+import os
+import sys
+
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(__dir__)
+sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '..')))
+
+from tools.infer_e2e import OpenOCR, OpenDetector, OpenRecognizer

openocr/configs/det/dbnet/repvit_db.yml

@@ -0,0 +1,173 @@
+Global:
+  device: gpu
+  epoch_num: &epoch_num 500
+  log_smooth_window: 20
+  print_batch_step: 100
+  save_model_dir: ./output/det_repsvtr_db
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 1000
+  cal_metric_during_train: false
+  checkpoints:
+  pretrained_model: openocr_det_repvit_ch.pth
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: ./testA
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+  model_type: det
+
+Architecture:
+  algorithm: DB
+  Backbone:
+    name: RepSVTR_det
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+# Loss:
+#   name: DBLoss
+#   balance_loss: true
+#   main_loss_type: DiceLoss
+#   alpha: 5
+#   beta: 10
+#   ohem_ratio: 3
+
+# Optimizer:
+#   name: Adam
+#   beta1: 0.9
+#   beta2: 0.999
+#   lr:
+#     name: Cosine
+#     learning_rate: 0.001 #(8*8c)
+#     warmup_epoch: 2
+#   regularizer:
+#     name: L2
+#     factor: 5.0e-05
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.4
+  max_candidates: 1000
+  unclip_ratio: 1.5
+  score_mode: 'slow'
+
+# Metric:
+#   name: DetMetric
+#   main_indicator: hmean
+
+# Train:
+#   dataset:
+#     name: SimpleDataSet
+#     data_dir: ./train_data/icdar2015/text_localization/
+#     label_file_list:
+#       - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+#     ratio_list: [1.0]
+#     transforms:
+#     - DecodeImage:
+#         img_mode: BGR
+#         channel_first: false
+#     - DetLabelEncode: null
+#     - CopyPaste: null
+#     - IaaAugment:
+#         augmenter_args:
+#         - type: Fliplr
+#           args:
+#             p: 0.5
+#         - type: Affine
+#           args:
+#             rotate:
+#             - -10
+#             - 10
+#         - type: Resize
+#           args:
+#             size:
+#             - 0.5
+#             - 3
+#     - EastRandomCropData:
+#         size:
+#         - 640
+#         - 640
+#         max_tries: 50
+#         keep_ratio: true
+#     - MakeBorderMap:
+#         shrink_ratio: 0.4
+#         thresh_min: 0.3
+#         thresh_max: 0.7
+#         total_epoch: *epoch_num
+#     - MakeShrinkMap:
+#         shrink_ratio: 0.4
+#         min_text_size: 8
+#         total_epoch: *epoch_num
+#     - NormalizeImage:
+#         scale: 1./255.
+#         mean:
+#         - 0.485
+#         - 0.456
+#         - 0.406
+#         std:
+#         - 0.229
+#         - 0.224
+#         - 0.225
+#         order: hwc
+#     - ToCHWImage: null
+#     - KeepKeys:
+#         keep_keys:
+#         - image
+#         - threshold_map
+#         - threshold_mask
+#         - shrink_map
+#         - shrink_mask
+#   loader:
+#     shuffle: true
+#     drop_last: false
+#     batch_size_per_card: 8
+#     num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest:
+        # image_shape: [1280, 1280]
+        # keep_ratio: True
+        # padding: True
+        limit_side_len: 960
+        limit_type: max
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
+profiler_options: null

openocr/configs/rec/abinet/resnet45_trans_abinet_lang.yml

@@ -0,0 +1,94 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/resnet45_trans_abinet_lang/
+  eval_epoch_step: [0, 1]
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model:
+  # ./openocr_nolang_abinet_lang.pth
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: ./tools/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  use_space_char: False
+  save_res_path: ./output/rec/u14m_filter/predicts_resnet45_trans_abinet_lang.txt
+  grad_clip_val: 20
+  use_amp: True
+
+Optimizer:
+  name: Adam
+  lr: 0.000267
+  weight_decay: 0.0
+  filter_bias_and_bn: False
+
+LRScheduler:
+  name: MultiStepLR
+  milestones: [12]
+  gamma: 0.1
+
+Architecture:
+  model_type: rec
+  algorithm: ABINet
+  Transform:
+  Encoder:
+    name: ResNet45
+    in_channels: 3
+    strides: [2, 1, 2, 1, 1]
+  Decoder:
+    name: ABINetDecoder
+    iter_size: 3
+
+Loss:
+  name: ABINetLoss
+
+PostProcess:
+  name: ABINetLabelDecode
+
+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:
+      - ABINetLabelEncode:
+      - RecTVResize:
+          image_shape: [32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ../evaluation
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - ABINetLabelEncode:
+      - RecTVResize:
+          image_shape: [32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 2

openocr/configs/rec/abinet/resnet45_trans_abinet_wo_lang.yml

@@ -0,0 +1,93 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/resnet45_trans_abinet_wo_lang/
+  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: ./tools/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  use_space_char: False
+  save_res_path: ./output/rec/u14m_filter/predicts_resnet45_trans_abinet_wo_lang.txt
+  grad_clip_val: 20
+  use_amp: True
+
+Optimizer:
+  name: Adam
+  lr: 0.000267
+  weight_decay: 0.0
+  filter_bias_and_bn: False
+
+LRScheduler:
+  name: MultiStepLR
+  milestones: [12]
+  gamma: 0.1
+
+Architecture:
+  model_type: rec
+  algorithm: ABINet
+  Transform:
+  Encoder:
+    name: ResNet45
+    in_channels: 3
+    strides: [2, 1, 2, 1, 1]
+  Decoder:
+    name: ABINetDecoder
+    iter_size: 0
+
+Loss:
+  name: ABINetLoss
+
+PostProcess:
+  name: ABINetLabelDecode
+
+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:
+      - ABINetLabelEncode:
+      - RecTVResize:
+          image_shape: [32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ../evaluation
+    transforms:
+      - DecodeImagePIL: # load image
+          img_mode: RGB
+      - ABINetLabelEncode:
+      - RecTVResize:
+          image_shape: [32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 2

openocr/configs/rec/abinet/svtrv2_abinet_lang.yml

@@ -0,0 +1,130 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/svtrv2_abinet_lang/
+  eval_epoch_step: [0, 1]
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model:
+  # ./openocr_svtrv2_nolang_abinet_lang.pth
+  checkpoints:
+  use_tensorboard: false
+  infer_img:
+  # for data or label process
+  character_dict_path: ./tools/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  use_space_char: False
+  save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_abinet_lang.txt
+  use_amp: True
+  grad_clip_val: 20
+
+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: ABINet
+  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: ABINetDecoder
+    iter_size: 3
+    num_layers: 0
+
+Loss:
+  name: ABINetLoss
+
+PostProcess:
+  name: ABINetLabelDecode
+
+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:
+      - ABINetLabelEncode:
+      - KeepKeys:
+          keep_keys: ['image', 'label', '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 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
+      - ABINetLabelEncode:
+      - KeepKeys:
+          keep_keys: ['image', 'label', '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/abinet/svtrv2_abinet_wo_lang.yml

@@ -0,0 +1,128 @@
+Global:
+  device: gpu
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 10
+  output_dir: ./output/rec/u14m_filter/svtrv2_abinet_wo_lang/
+  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: ./tools/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  use_space_char: False
+  save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_abinet_wo_lang.txt
+  use_amp: True
+  grad_clip_val: 20
+
+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: ABINet
+  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: ABINetDecoder
+    iter_size: 0
+    num_layers: 0
+Loss:
+  name: ABINetLoss
+
+PostProcess:
+  name: ABINetLabelDecode
+
+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:
+      - ABINetLabelEncode:
+      - KeepKeys:
+          keep_keys: ['image', 'label', '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 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
+      - ABINetLabelEncode:
+      - KeepKeys:
+          keep_keys: ['image', 'label', '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