refactor(model): update OCR model and remove unused configs

- Remove unused UniMERNet and LayoutLMv3 model configurations
- Update OCR model path and dictionary path for PaddleOCR
- Modify README to update system requirements and installation instructions
- Update setup.py to include new package data

README_zh-CN.md

@@ -216,7 +216,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
     </tr>
     <tr>
         <td colspan="3">python版本</td>
-        <td colspan="3">3.10 (请务必通过conda创建3.10虚拟环境)</td>
+        <td colspan="3">>=3.9,<=3.12</td>
     </tr>
     <tr>
         <td colspan="3">Nvidia Driver 版本</td>
@@ -226,8 +226,8 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
     </tr>
     <tr>
         <td colspan="3">CUDA环境</td>
-        <td>自动安装[12.1(pytorch)+11.8(paddle)]</td>
-        <td>11.8(手动安装)+cuDNN v8.7.0(手动安装)</td>
+        <td>11.8/12.4/12.6</td>
+        <td>11.8/12.4/12.6</td>
         <td>None</td>
     </tr>
     <tr>
@@ -237,12 +237,12 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
         <td>None</td>
     </tr>
     <tr>
-        <td rowspan="2">GPU硬件支持列表</td>
-        <td colspan="2">显存8G以上</td>
+        <td rowspan="2">GPU/MPS 硬件支持列表</td>
+        <td colspan="2">显存6G以上</td>
         <td colspan="2">
-        2080~2080Ti / 3060Ti~3090Ti / 4060~4090<br>
-        8G显存及以上可开启全部加速功能</td>
-        <td rowspan="2">None</td>
+        Volta(2017)及之后生产的全部带Tensor Core的GPU <br>
+        6G显存及以上</td>
+        <td rowspan="2">apple slicon</td>
     </tr>
 </table>
 
@@ -262,9 +262,9 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 > 最新版本国内镜像源同步可能会有延迟，请耐心等待
 
 ```bash
-conda create -n mineru python=3.10
+conda create -n mineru 'python<3.13' -y
 conda activate mineru
-pip install -U "magic-pdf[full]" --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
+pip install -U "magic-pdf[full]" -i https://mirrors.aliyun.com/pypi/simple
 ```
 
 #### 2. 下载模型权重文件

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorch_paddle.py

@@ -63,14 +63,14 @@ class PytorchPaddleOCR(TextSystem):
         else:
             pass
 
-        models_config_path = os.path.join(root_dir, 'models_config.yml')
+        models_config_path = os.path.join(root_dir, 'pytorchocr', 'utils', 'resources', 'models_config.yml')
         with open(models_config_path) as file:
             config = yaml.safe_load(file)
             det, rec, dict_file = get_model_params(self.lang, config)
         ocr_models_dir = os.path.join(get_local_models_dir(), 'OCR', 'paddleocr_torch')
         kwargs['det_model_path'] = os.path.join(ocr_models_dir, det)
         kwargs['rec_model_path'] = os.path.join(ocr_models_dir, rec)
-        kwargs['rec_char_dict_path'] = os.path.join(root_dir, 'pytorchocr', 'utils', 'dict', dict_file)
+        kwargs['rec_char_dict_path'] = os.path.join(root_dir, 'pytorchocr', 'utils', 'resources', 'dict', dict_file)
 
         kwargs['device'] = get_device()
 

magic_pdf/resources/model_config/UniMERNet/demo.yaml

@@ -1,46 +0,0 @@
-model:
-  arch: unimernet
-  model_type: unimernet
-  model_config:
-    model_name: ./models/unimernet_base
-    max_seq_len: 1536
-
-  load_pretrained: True
-  pretrained: './models/unimernet_base/pytorch_model.pth'
-  tokenizer_config:
-    path: ./models/unimernet_base
-
-datasets:
-  formula_rec_eval:
-    vis_processor:
-      eval:
-        name: "formula_image_eval"
-        image_size:
-          - 192
-          - 672
-
-run:
-  runner: runner_iter
-  task: unimernet_train
-
-  batch_size_train: 64
-  batch_size_eval: 64
-  num_workers: 1
-
-  iters_per_inner_epoch: 2000
-  max_iters: 60000
-
-  seed: 42
-  output_dir: "../output/demo"
-
-  evaluate: True
-  test_splits: [ "eval" ]
-
-  device: "cuda"
-  world_size: 1
-  dist_url: "env://"
-  distributed: True
-  distributed_type: ddp  # or fsdp when train llm
-
-  generate_cfg:
-    temperature: 0.0

magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml

@@ -1,351 +0,0 @@
-AUG:
-  DETR: true
-CACHE_DIR: ~/cache/huggingface
-CUDNN_BENCHMARK: false
-DATALOADER:
-  ASPECT_RATIO_GROUPING: true
-  FILTER_EMPTY_ANNOTATIONS: false
-  NUM_WORKERS: 4
-  REPEAT_THRESHOLD: 0.0
-  SAMPLER_TRAIN: TrainingSampler
-DATASETS:
-  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
-  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
-  PROPOSAL_FILES_TEST: []
-  PROPOSAL_FILES_TRAIN: []
-  TEST:
-  - scihub_train
-  TRAIN:
-  - scihub_train
-GLOBAL:
-  HACK: 1.0
-ICDAR_DATA_DIR_TEST: ''
-ICDAR_DATA_DIR_TRAIN: ''
-INPUT:
-  CROP:
-    ENABLED: true
-    SIZE:
-    - 384
-    - 600
-    TYPE: absolute_range
-  FORMAT: RGB
-  MASK_FORMAT: polygon
-  MAX_SIZE_TEST: 1333
-  MAX_SIZE_TRAIN: 1333
-  MIN_SIZE_TEST: 800
-  MIN_SIZE_TRAIN:
-  - 480
-  - 512
-  - 544
-  - 576
-  - 608
-  - 640
-  - 672
-  - 704
-  - 736
-  - 768
-  - 800
-  MIN_SIZE_TRAIN_SAMPLING: choice
-  RANDOM_FLIP: horizontal
-MODEL:
-  ANCHOR_GENERATOR:
-    ANGLES:
-    - - -90
-      - 0
-      - 90
-    ASPECT_RATIOS:
-    - - 0.5
-      - 1.0
-      - 2.0
-    NAME: DefaultAnchorGenerator
-    OFFSET: 0.0
-    SIZES:
-    - - 32
-    - - 64
-    - - 128
-    - - 256
-    - - 512
-  BACKBONE:
-    FREEZE_AT: 2
-    NAME: build_vit_fpn_backbone
-  CONFIG_PATH: ''
-  DEVICE: cuda
-  FPN:
-    FUSE_TYPE: sum
-    IN_FEATURES:
-    - layer3
-    - layer5
-    - layer7
-    - layer11
-    NORM: ''
-    OUT_CHANNELS: 256
-  IMAGE_ONLY: true
-  KEYPOINT_ON: false
-  LOAD_PROPOSALS: false
-  MASK_ON: true
-  META_ARCHITECTURE: VLGeneralizedRCNN
-  PANOPTIC_FPN:
-    COMBINE:
-      ENABLED: true
-      INSTANCES_CONFIDENCE_THRESH: 0.5
-      OVERLAP_THRESH: 0.5
-      STUFF_AREA_LIMIT: 4096
-    INSTANCE_LOSS_WEIGHT: 1.0
-  PIXEL_MEAN:
-  - 127.5
-  - 127.5
-  - 127.5
-  PIXEL_STD:
-  - 127.5
-  - 127.5
-  - 127.5
-  PROPOSAL_GENERATOR:
-    MIN_SIZE: 0
-    NAME: RPN
-  RESNETS:
-    DEFORM_MODULATED: false
-    DEFORM_NUM_GROUPS: 1
-    DEFORM_ON_PER_STAGE:
-    - false
-    - false
-    - false
-    - false
-    DEPTH: 50
-    NORM: FrozenBN
-    NUM_GROUPS: 1
-    OUT_FEATURES:
-    - res4
-    RES2_OUT_CHANNELS: 256
-    RES5_DILATION: 1
-    STEM_OUT_CHANNELS: 64
-    STRIDE_IN_1X1: true
-    WIDTH_PER_GROUP: 64
-  RETINANET:
-    BBOX_REG_LOSS_TYPE: smooth_l1
-    BBOX_REG_WEIGHTS:
-    - 1.0
-    - 1.0
-    - 1.0
-    - 1.0
-    FOCAL_LOSS_ALPHA: 0.25
-    FOCAL_LOSS_GAMMA: 2.0
-    IN_FEATURES:
-    - p3
-    - p4
-    - p5
-    - p6
-    - p7
-    IOU_LABELS:
-    - 0
-    - -1
-    - 1
-    IOU_THRESHOLDS:
-    - 0.4
-    - 0.5
-    NMS_THRESH_TEST: 0.5
-    NORM: ''
-    NUM_CLASSES: 10
-    NUM_CONVS: 4
-    PRIOR_PROB: 0.01
-    SCORE_THRESH_TEST: 0.05
-    SMOOTH_L1_LOSS_BETA: 0.1
-    TOPK_CANDIDATES_TEST: 1000
-  ROI_BOX_CASCADE_HEAD:
-    BBOX_REG_WEIGHTS:
-    - - 10.0
-      - 10.0
-      - 5.0
-      - 5.0
-    - - 20.0
-      - 20.0
-      - 10.0
-      - 10.0
-    - - 30.0
-      - 30.0
-      - 15.0
-      - 15.0
-    IOUS:
-    - 0.5
-    - 0.6
-    - 0.7
-  ROI_BOX_HEAD:
-    BBOX_REG_LOSS_TYPE: smooth_l1
-    BBOX_REG_LOSS_WEIGHT: 1.0
-    BBOX_REG_WEIGHTS:
-    - 10.0
-    - 10.0
-    - 5.0
-    - 5.0
-    CLS_AGNOSTIC_BBOX_REG: true
-    CONV_DIM: 256
-    FC_DIM: 1024
-    NAME: FastRCNNConvFCHead
-    NORM: ''
-    NUM_CONV: 0
-    NUM_FC: 2
-    POOLER_RESOLUTION: 7
-    POOLER_SAMPLING_RATIO: 0
-    POOLER_TYPE: ROIAlignV2
-    SMOOTH_L1_BETA: 0.0
-    TRAIN_ON_PRED_BOXES: false
-  ROI_HEADS:
-    BATCH_SIZE_PER_IMAGE: 512
-    IN_FEATURES:
-    - p2
-    - p3
-    - p4
-    - p5
-    IOU_LABELS:
-    - 0
-    - 1
-    IOU_THRESHOLDS:
-    - 0.5
-    NAME: CascadeROIHeads
-    NMS_THRESH_TEST: 0.5
-    NUM_CLASSES: 10
-    POSITIVE_FRACTION: 0.25
-    PROPOSAL_APPEND_GT: true
-    SCORE_THRESH_TEST: 0.05
-  ROI_KEYPOINT_HEAD:
-    CONV_DIMS:
-    - 512
-    - 512
-    - 512
-    - 512
-    - 512
-    - 512
-    - 512
-    - 512
-    LOSS_WEIGHT: 1.0
-    MIN_KEYPOINTS_PER_IMAGE: 1
-    NAME: KRCNNConvDeconvUpsampleHead
-    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
-    NUM_KEYPOINTS: 17
-    POOLER_RESOLUTION: 14
-    POOLER_SAMPLING_RATIO: 0
-    POOLER_TYPE: ROIAlignV2
-  ROI_MASK_HEAD:
-    CLS_AGNOSTIC_MASK: false
-    CONV_DIM: 256
-    NAME: MaskRCNNConvUpsampleHead
-    NORM: ''
-    NUM_CONV: 4
-    POOLER_RESOLUTION: 14
-    POOLER_SAMPLING_RATIO: 0
-    POOLER_TYPE: ROIAlignV2
-  RPN:
-    BATCH_SIZE_PER_IMAGE: 256
-    BBOX_REG_LOSS_TYPE: smooth_l1
-    BBOX_REG_LOSS_WEIGHT: 1.0
-    BBOX_REG_WEIGHTS:
-    - 1.0
-    - 1.0
-    - 1.0
-    - 1.0
-    BOUNDARY_THRESH: -1
-    CONV_DIMS:
-    - -1
-    HEAD_NAME: StandardRPNHead
-    IN_FEATURES:
-    - p2
-    - p3
-    - p4
-    - p5
-    - p6
-    IOU_LABELS:
-    - 0
-    - -1
-    - 1
-    IOU_THRESHOLDS:
-    - 0.3
-    - 0.7
-    LOSS_WEIGHT: 1.0
-    NMS_THRESH: 0.7
-    POSITIVE_FRACTION: 0.5
-    POST_NMS_TOPK_TEST: 1000
-    POST_NMS_TOPK_TRAIN: 2000
-    PRE_NMS_TOPK_TEST: 1000
-    PRE_NMS_TOPK_TRAIN: 2000
-    SMOOTH_L1_BETA: 0.0
-  SEM_SEG_HEAD:
-    COMMON_STRIDE: 4
-    CONVS_DIM: 128
-    IGNORE_VALUE: 255
-    IN_FEATURES:
-    - p2
-    - p3
-    - p4
-    - p5
-    LOSS_WEIGHT: 1.0
-    NAME: SemSegFPNHead
-    NORM: GN
-    NUM_CLASSES: 10
-  VIT:
-    DROP_PATH: 0.1
-    IMG_SIZE:
-    - 224
-    - 224
-    NAME: layoutlmv3_base
-    OUT_FEATURES:
-    - layer3
-    - layer5
-    - layer7
-    - layer11
-    POS_TYPE: abs
-  WEIGHTS: 
-OUTPUT_DIR: 
-SCIHUB_DATA_DIR_TRAIN: ~/publaynet/layout_scihub/train
-SEED: 42
-SOLVER:
-  AMP:
-    ENABLED: true
-  BACKBONE_MULTIPLIER: 1.0
-  BASE_LR: 0.0002
-  BIAS_LR_FACTOR: 1.0
-  CHECKPOINT_PERIOD: 2000
-  CLIP_GRADIENTS:
-    CLIP_TYPE: full_model
-    CLIP_VALUE: 1.0
-    ENABLED: true
-    NORM_TYPE: 2.0
-  GAMMA: 0.1
-  GRADIENT_ACCUMULATION_STEPS: 1
-  IMS_PER_BATCH: 32
-  LR_SCHEDULER_NAME: WarmupCosineLR
-  MAX_ITER: 20000
-  MOMENTUM: 0.9
-  NESTEROV: false
-  OPTIMIZER: ADAMW
-  REFERENCE_WORLD_SIZE: 0
-  STEPS:
-  - 10000
-  WARMUP_FACTOR: 0.01
-  WARMUP_ITERS: 333
-  WARMUP_METHOD: linear
-  WEIGHT_DECAY: 0.05
-  WEIGHT_DECAY_BIAS: null
-  WEIGHT_DECAY_NORM: 0.0
-TEST:
-  AUG:
-    ENABLED: false
-    FLIP: true
-    MAX_SIZE: 4000
-    MIN_SIZES:
-    - 400
-    - 500
-    - 600
-    - 700
-    - 800
-    - 900
-    - 1000
-    - 1100
-    - 1200
-  DETECTIONS_PER_IMAGE: 100
-  EVAL_PERIOD: 1000
-  EXPECTED_RESULTS: []
-  KEYPOINT_OKS_SIGMAS: []
-  PRECISE_BN:
-    ENABLED: false
-    NUM_ITER: 200
-VERSION: 2
-VIS_PERIOD: 0

setup.py

@@ -26,9 +26,10 @@ if __name__ == '__main__':
     setup(
         name="magic_pdf",  # 项目名
         version=__version__,  # 自动从tag中获取版本号
-        packages=find_packages() + ["magic_pdf.resources"],  # 包含所有的包
+        packages=find_packages() + ["magic_pdf.resources"] + ["magic_pdf.model.sub_modules.ocr.paddleocr2pytorch.pytorchocr.utils.resources"],  # 包含所有的包
         package_data={
             "magic_pdf.resources": ["**"],  # 包含magic_pdf.resources目录下的所有文件
+            "magic_pdf.model.sub_modules.ocr.paddleocr2pytorch.pytorchocr.utils.resources": ["**"],  # pytorchocr.resources目录下的所有文件
         },
         install_requires=parse_requirements('requirements.txt'),  # 项目依赖的第三方库
         extras_require={
@@ -41,9 +42,10 @@ if __name__ == '__main__':
                      "matplotlib;platform_system=='Linux' or platform_system=='Darwin'",  # linux 和 macos 不应限制matplotlib的最高版本，以避免无法更新导致的一些bug
                      "ultralytics>=8.3.48",  # yolov8,公式检测
                      "doclayout_yolo==0.0.2b1",  # doclayout_yolo
+                     "dill",  # doclayout_yolo
                      "rapid_table>=1.0.3,<2.0.0",  # rapid_table
                      "PyYAML",  # yaml
-                     "ftfy"
+                     "ftfy", # unimernet_hf
                      "openai",  # openai SDK
                      ],
             "old_linux":[