!11 Update version.py with new version

Merge pull request !11 from zhch158/master

.github/workflows/cla.yml

@@ -18,9 +18,9 @@ jobs:
     steps:
       - name: "CLA Assistant"
         if: (github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA') || github.event_name == 'pull_request_target'
-        uses: contributor-assistant/github-action@v2.5.0
+        uses: contributor-assistant/github-action@v2.6.1
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN  }}
           # the below token should have repo scope and must be manually added by you in the repository's secret
           # This token is required only if you have configured to store the signatures in a remote repository/organization
           PERSONAL_ACCESS_TOKEN: ${{ secrets.RELEASE_TOKEN }}
@@ -28,7 +28,7 @@ jobs:
           path-to-signatures: 'signatures/version1/cla.json'
           path-to-document: 'https://github.com/opendatalab/MinerU/blob/master/MinerU_CLA.md' # e.g. a CLA or a DCO document
           # branch should not be protected
-          branch: 'master'
+          branch: 'cla'
           allowlist: myhloli,dt-yy,Focusshang,renpengli01,icecraft,drunkpig,wangbinDL,qiangqiang199,GDDGCZ518,papayalove,conghui,quyuan,LollipopsAndWine,Sidney233
 
          # the followings are the optional inputs - If the optional inputs are not given, then default values will be taken

.github/workflows/cli.yml

@@ -1,16 +1,15 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: mineru
+name: mineru-cli-test
 on:
-  pull_request:
+  push:
     branches:
       - "master"
       - "dev"
     paths-ignore:
       - "cmds/**"
       - "**.md"
-  workflow_dispatch:
 jobs:
   cli-test:
     if: github.repository == 'opendatalab/MinerU'
@@ -20,31 +19,30 @@ jobs:
       fail-fast: true
 
     steps:
-    - name: PDF cli
-      uses: actions/checkout@v4
-      with:
-        ref: dev
-        fetch-depth: 2
+      - name: PDF cli
+        uses: actions/checkout@v4
+        with:
+          ref: dev
+          fetch-depth: 2
 
-    - name: install uv
-      uses: astral-sh/setup-uv@v5
-
-    - name: install&test
-      run: |
-        uv --version
-        uv venv --python 3.12
-        source .venv/bin/activate
-        uv pip install .[test]
-        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
-        cd $GITHUB_WORKSPACE && coverage run
-        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
+      - name: install uv
+        uses: astral-sh/setup-uv@v5
 
+      - name: install&test
+        run: |
+          uv --version
+          uv venv --python 3.12
+          source .venv/bin/activate
+          uv pip install .[test]
+          cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
+          cd $GITHUB_WORKSPACE && coverage run
+          cd $GITHUB_WORKSPACE && python tests/get_coverage.py
 
   notify_to_feishu:
     if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure')}}
     needs: cli-test
     runs-on: ubuntu-latest
     steps:
-    - name: notify
-      run: |
-        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}
+      - name: notify
+        run: |
+          curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}

.github/workflows/huigui.yml

@@ -1,48 +0,0 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
-
-name: mineru
-on:
-  push:
-    branches:
-      - "master"
-      - "dev"
-    paths-ignore:
-      - "cmds/**"
-      - "**.md"
-jobs:
-  cli-test:
-    if: github.repository == 'opendatalab/MinerU'
-    runs-on: ubuntu-latest
-    timeout-minutes: 240
-    strategy:
-      fail-fast: true
-
-    steps:
-    - name: PDF cli
-      uses: actions/checkout@v4
-      with:
-        ref: dev
-        fetch-depth: 2
-
-    - name: install uv
-      uses: astral-sh/setup-uv@v5
-
-    - name: install&test
-      run: |
-        uv --version
-        uv venv --python 3.12
-        source .venv/bin/activate
-        uv pip install .[test]
-        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
-        cd $GITHUB_WORKSPACE && coverage run
-        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
-
-  notify_to_feishu:
-    if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure')}}
-    needs: cli-test
-    runs-on: ubuntu-latest
-    steps:
-    - name: notify
-      run: |
-        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}

README.md

@@ -43,7 +43,10 @@
 </div>
 
 # Changelog
-
+- 2025/07/23 2.1.4 Released
+  - Bug Fixes
+    - Fixed the issue of excessive memory consumption during the `MFR` step in the `pipeline` backend under certain scenarios #2771
+    - Fixed the inaccurate matching between `image`/`table` and `caption`/`footnote` under certain conditions #3129
 - 2025/07/16 2.1.1 Released
   - Bug fixes
     - Fixed text block content loss issue that could occur in certain `pipeline` scenarios #3005

README_zh-CN.md

@@ -43,6 +43,10 @@
 </div>
 
 # 更新记录
+- 2025/07/23 2.1.4发布
+  - bug修复
+    - 修复`pipeline`后端中`MFR`步骤在某些情况下显存消耗过大的问题 #2771
+    - 修复某些情况下`image`/`table`与`caption`/`footnote`匹配不准确的问题 #3129
 - 2025/07/16 2.1.1发布
   - bug修复 
     - 修复`pipeline`在某些情况可能发生的文本块内容丢失问题 #3005

mineru/backend/pipeline/batch_analyze.py

@@ -12,6 +12,7 @@ from ...utils.ocr_utils import get_adjusted_mfdetrec_res, get_ocr_result_list, O
 YOLO_LAYOUT_BASE_BATCH_SIZE = 8
 MFD_BASE_BATCH_SIZE = 1
 MFR_BASE_BATCH_SIZE = 16
+OCR_DET_BASE_BATCH_SIZE = 16
 
 
 class BatchAnalyze:
@@ -170,9 +171,9 @@ class BatchAnalyze:
                         batch_images.append(padded_img)
 
                     # 批处理检测
-                    batch_size = min(len(batch_images), self.batch_ratio * 16)  # 增加批处理大小
-                    # logger.debug(f"OCR-det batch: {batch_size} images, target size: {target_h}x{target_w}")
-                    batch_results = ocr_model.text_detector.batch_predict(batch_images, batch_size)
+                    det_batch_size = min(len(batch_images), self.batch_ratio * OCR_DET_BASE_BATCH_SIZE)  # 增加批处理大小
+                    # logger.debug(f"OCR-det batch: {det_batch_size} images, target size: {target_h}x{target_w}")
+                    batch_results = ocr_model.text_detector.batch_predict(batch_images, det_batch_size)
 
                     # 处理批处理结果
                     for i, (crop_info, (dt_boxes, elapse)) in enumerate(zip(group_crops, batch_results)):

mineru/backend/pipeline/pipeline_analyze.py

@@ -74,10 +74,10 @@ def doc_analyze(
         table_enable=True,
 ):
     """
-    适当调大MIN_BATCH_INFERENCE_SIZE可以提高性能，可能会增加显存使用量，
-    可通过环境变量MINERU_MIN_BATCH_INFERENCE_SIZE设置，默认值为128。
+    适当调大MIN_BATCH_INFERENCE_SIZE可以提高性能，更大的 MIN_BATCH_INFERENCE_SIZE会消耗更多内存，
+    可通过环境变量MINERU_MIN_BATCH_INFERENCE_SIZE设置，默认值为384。
     """
-    min_batch_inference_size = int(os.environ.get('MINERU_MIN_BATCH_INFERENCE_SIZE', 128))
+    min_batch_inference_size = int(os.environ.get('MINERU_MIN_BATCH_INFERENCE_SIZE', 384))
 
     # 收集所有页面信息
     all_pages_info = []  # 存储(dataset_index, page_index, img, ocr, lang, width, height)

mineru/backend/pipeline/pipeline_magic_model.py

@@ -1,5 +1,6 @@
-from mineru.utils.boxbase import bbox_relative_pos, calculate_iou, bbox_distance, is_in, get_minbox_if_overlap_by_ratio
+from mineru.utils.boxbase import bbox_relative_pos, calculate_iou, bbox_distance, get_minbox_if_overlap_by_ratio
 from mineru.utils.enum_class import CategoryId, ContentType
+from mineru.utils.magic_model_utils import tie_up_category_by_distance_v3, reduct_overlap
 
 
 class MagicModel:
@@ -208,168 +209,39 @@ class MagicModel:
 
         return bbox_distance(bbox1, bbox2)
 
-    def __reduct_overlap(self, bboxes):
-        N = len(bboxes)
-        keep = [True] * N
-        for i in range(N):
-            for j in range(N):
-                if i == j:
-                    continue
-                if is_in(bboxes[i]['bbox'], bboxes[j]['bbox']):
-                    keep[i] = False
-        return [bboxes[i] for i in range(N) if keep[i]]
-
-    def __tie_up_category_by_distance_v3(
-        self,
-        subject_category_id: int,
-        object_category_id: int,
-    ):
-        subjects = self.__reduct_overlap(
-            list(
-                map(
-                    lambda x: {'bbox': x['bbox'], 'score': x['score']},
-                    filter(
-                        lambda x: x['category_id'] == subject_category_id,
-                        self.__page_model_info['layout_dets'],
-                    ),
-                )
-            )
-        )
-        objects = self.__reduct_overlap(
-            list(
-                map(
-                    lambda x: {'bbox': x['bbox'], 'score': x['score']},
-                    filter(
-                        lambda x: x['category_id'] == object_category_id,
-                        self.__page_model_info['layout_dets'],
-                    ),
+    def __tie_up_category_by_distance_v3(self, subject_category_id, object_category_id):
+        # 定义获取主体和客体对象的函数
+        def get_subjects():
+            return reduct_overlap(
+                list(
+                    map(
+                        lambda x: {'bbox': x['bbox'], 'score': x['score']},
+                        filter(
+                            lambda x: x['category_id'] == subject_category_id,
+                            self.__page_model_info['layout_dets'],
+                        ),
+                    )
                 )
             )
-        )
-
-        ret = []
-        N, M = len(subjects), len(objects)
-        subjects.sort(key=lambda x: x['bbox'][0] ** 2 + x['bbox'][1] ** 2)
-        objects.sort(key=lambda x: x['bbox'][0] ** 2 + x['bbox'][1] ** 2)
-
-        OBJ_IDX_OFFSET = 10000
-        SUB_BIT_KIND, OBJ_BIT_KIND = 0, 1
-
-        all_boxes_with_idx = [(i, SUB_BIT_KIND, sub['bbox'][0], sub['bbox'][1]) for i, sub in enumerate(subjects)] + [(i + OBJ_IDX_OFFSET , OBJ_BIT_KIND, obj['bbox'][0], obj['bbox'][1]) for i, obj in enumerate(objects)]
-        seen_idx = set()
-        seen_sub_idx = set()
-
-        while N > len(seen_sub_idx):
-            candidates = []
-            for idx, kind, x0, y0 in all_boxes_with_idx:
-                if idx in seen_idx:
-                    continue
-                candidates.append((idx, kind, x0, y0))
-
-            if len(candidates) == 0:
-                break
-            left_x = min([v[2] for v in candidates])
-            top_y =  min([v[3] for v in candidates])
-
-            candidates.sort(key=lambda x: (x[2]-left_x) ** 2 + (x[3] - top_y) ** 2)
-
-
-            fst_idx, fst_kind, left_x, top_y = candidates[0]
-            candidates.sort(key=lambda x: (x[2] - left_x) ** 2 + (x[3] - top_y)**2)
-            nxt = None
-
-            for i in range(1, len(candidates)):
-                if candidates[i][1] ^ fst_kind == 1:
-                    nxt = candidates[i]
-                    break
-            if nxt is None:
-                break
-
-            if fst_kind == SUB_BIT_KIND:
-                sub_idx, obj_idx = fst_idx, nxt[0] - OBJ_IDX_OFFSET
 
-            else:
-                sub_idx, obj_idx = nxt[0], fst_idx - OBJ_IDX_OFFSET
-
-            pair_dis = bbox_distance(subjects[sub_idx]['bbox'], objects[obj_idx]['bbox'])
-            nearest_dis = float('inf')
-            for i in range(N):
-                if i in seen_idx or i == sub_idx:continue
-                nearest_dis = min(nearest_dis, bbox_distance(subjects[i]['bbox'], objects[obj_idx]['bbox']))
-
-            if pair_dis >= 3*nearest_dis:
-                seen_idx.add(sub_idx)
-                continue
-
-            seen_idx.add(sub_idx)
-            seen_idx.add(obj_idx + OBJ_IDX_OFFSET)
-            seen_sub_idx.add(sub_idx)
-
-            ret.append(
-                {
-                    'sub_bbox': {
-                        'bbox': subjects[sub_idx]['bbox'],
-                        'score': subjects[sub_idx]['score'],
-                    },
-                    'obj_bboxes': [
-                        {'score': objects[obj_idx]['score'], 'bbox': objects[obj_idx]['bbox']}
-                    ],
-                    'sub_idx': sub_idx,
-                }
-            )
-
-        for i in range(len(objects)):
-            j = i + OBJ_IDX_OFFSET
-            if j in seen_idx:
-                continue
-            seen_idx.add(j)
-            nearest_dis, nearest_sub_idx = float('inf'), -1
-            for k in range(len(subjects)):
-                dis = bbox_distance(objects[i]['bbox'], subjects[k]['bbox'])
-                if dis < nearest_dis:
-                    nearest_dis = dis
-                    nearest_sub_idx = k
-
-            for k in range(len(subjects)):
-                if k != nearest_sub_idx: continue
-                if k in seen_sub_idx:
-                    for kk in range(len(ret)):
-                        if ret[kk]['sub_idx'] == k:
-                            ret[kk]['obj_bboxes'].append({'score': objects[i]['score'], 'bbox': objects[i]['bbox']})
-                            break
-                else:
-                    ret.append(
-                        {
-                            'sub_bbox': {
-                                'bbox': subjects[k]['bbox'],
-                                'score': subjects[k]['score'],
-                            },
-                            'obj_bboxes': [
-                                {'score': objects[i]['score'], 'bbox': objects[i]['bbox']}
-                            ],
-                            'sub_idx': k,
-                        }
+        def get_objects():
+            return reduct_overlap(
+                list(
+                    map(
+                        lambda x: {'bbox': x['bbox'], 'score': x['score']},
+                        filter(
+                            lambda x: x['category_id'] == object_category_id,
+                            self.__page_model_info['layout_dets'],
+                        ),
                     )
-                seen_sub_idx.add(k)
-                seen_idx.add(k)
-
-
-        for i in range(len(subjects)):
-            if i in seen_sub_idx:
-                continue
-            ret.append(
-                {
-                    'sub_bbox': {
-                        'bbox': subjects[i]['bbox'],
-                        'score': subjects[i]['score'],
-                    },
-                    'obj_bboxes': [],
-                    'sub_idx': i,
-                }
+                )
             )
 
-
-        return ret
+        # 调用通用方法
+        return tie_up_category_by_distance_v3(
+            get_subjects,
+            get_objects
+        )
 
     def get_imgs(self):
         with_captions = self.__tie_up_category_by_distance_v3(

mineru/backend/vlm/vlm_magic_model.py

@@ -3,10 +3,10 @@ from typing import Literal
 
 from loguru import logger
 
-from mineru.utils.boxbase import bbox_distance, is_in
 from mineru.utils.enum_class import ContentType, BlockType, SplitFlag
 from mineru.backend.vlm.vlm_middle_json_mkcontent import merge_para_with_text
 from mineru.utils.format_utils import convert_otsl_to_html
+from mineru.utils.magic_model_utils import reduct_overlap, tie_up_category_by_distance_v3
 
 
 class MagicModel:
@@ -251,175 +251,39 @@ def latex_fix(latex):
     return latex
 
 
-def __reduct_overlap(bboxes):
-    N = len(bboxes)
-    keep = [True] * N
-    for i in range(N):
-        for j in range(N):
-            if i == j:
-                continue
-            if is_in(bboxes[i]["bbox"], bboxes[j]["bbox"]):
-                keep[i] = False
-    return [bboxes[i] for i in range(N) if keep[i]]
-
-
-def __tie_up_category_by_distance_v3(
-    blocks: list,
-    subject_block_type: str,
-    object_block_type: str,
-):
-    subjects = __reduct_overlap(
-        list(
-            map(
-                lambda x: {"bbox": x["bbox"], "lines": x["lines"], "index": x["index"]},
-                filter(
-                    lambda x: x["type"] == subject_block_type,
-                    blocks,
-                ),
-            )
-        )
-    )
-    objects = __reduct_overlap(
-        list(
-            map(
-                lambda x: {"bbox": x["bbox"], "lines": x["lines"], "index": x["index"]},
-                filter(
-                    lambda x: x["type"] == object_block_type,
-                    blocks,
-                ),
+def __tie_up_category_by_distance_v3(blocks, subject_block_type, object_block_type):
+    # 定义获取主体和客体对象的函数
+    def get_subjects():
+        return reduct_overlap(
+            list(
+                map(
+                    lambda x: {"bbox": x["bbox"], "lines": x["lines"], "index": x["index"]},
+                    filter(
+                        lambda x: x["type"] == subject_block_type,
+                        blocks,
+                    ),
+                )
             )
         )
-    )
 
-    ret = []
-    N, M = len(subjects), len(objects)
-    subjects.sort(key=lambda x: x["bbox"][0] ** 2 + x["bbox"][1] ** 2)
-    objects.sort(key=lambda x: x["bbox"][0] ** 2 + x["bbox"][1] ** 2)
-
-    OBJ_IDX_OFFSET = 10000
-    SUB_BIT_KIND, OBJ_BIT_KIND = 0, 1
-
-    all_boxes_with_idx = [(i, SUB_BIT_KIND, sub["bbox"][0], sub["bbox"][1]) for i, sub in enumerate(subjects)] + [
-        (i + OBJ_IDX_OFFSET, OBJ_BIT_KIND, obj["bbox"][0], obj["bbox"][1]) for i, obj in enumerate(objects)
-    ]
-    seen_idx = set()
-    seen_sub_idx = set()
-
-    while N > len(seen_sub_idx):
-        candidates = []
-        for idx, kind, x0, y0 in all_boxes_with_idx:
-            if idx in seen_idx:
-                continue
-            candidates.append((idx, kind, x0, y0))
-
-        if len(candidates) == 0:
-            break
-        left_x = min([v[2] for v in candidates])
-        top_y = min([v[3] for v in candidates])
-
-        candidates.sort(key=lambda x: (x[2] - left_x) ** 2 + (x[3] - top_y) ** 2)
-
-        fst_idx, fst_kind, left_x, top_y = candidates[0]
-        candidates.sort(key=lambda x: (x[2] - left_x) ** 2 + (x[3] - top_y) ** 2)
-        nxt = None
-
-        for i in range(1, len(candidates)):
-            if candidates[i][1] ^ fst_kind == 1:
-                nxt = candidates[i]
-                break
-        if nxt is None:
-            break
-
-        if fst_kind == SUB_BIT_KIND:
-            sub_idx, obj_idx = fst_idx, nxt[0] - OBJ_IDX_OFFSET
-
-        else:
-            sub_idx, obj_idx = nxt[0], fst_idx - OBJ_IDX_OFFSET
-
-        pair_dis = bbox_distance(subjects[sub_idx]["bbox"], objects[obj_idx]["bbox"])
-        nearest_dis = float("inf")
-        for i in range(N):
-            if i in seen_idx or i == sub_idx:
-                continue
-            nearest_dis = min(nearest_dis, bbox_distance(subjects[i]["bbox"], objects[obj_idx]["bbox"]))
-
-        if pair_dis >= 3 * nearest_dis:
-            seen_idx.add(sub_idx)
-            continue
-
-        seen_idx.add(sub_idx)
-        seen_idx.add(obj_idx + OBJ_IDX_OFFSET)
-        seen_sub_idx.add(sub_idx)
-
-        ret.append(
-            {
-                "sub_bbox": {
-                    "bbox": subjects[sub_idx]["bbox"],
-                    "lines": subjects[sub_idx]["lines"],
-                    "index": subjects[sub_idx]["index"],
-                },
-                "obj_bboxes": [
-                    {"bbox": objects[obj_idx]["bbox"], "lines": objects[obj_idx]["lines"], "index": objects[obj_idx]["index"]}
-                ],
-                "sub_idx": sub_idx,
-            }
-        )
-
-    for i in range(len(objects)):
-        j = i + OBJ_IDX_OFFSET
-        if j in seen_idx:
-            continue
-        seen_idx.add(j)
-        nearest_dis, nearest_sub_idx = float("inf"), -1
-        for k in range(len(subjects)):
-            dis = bbox_distance(objects[i]["bbox"], subjects[k]["bbox"])
-            if dis < nearest_dis:
-                nearest_dis = dis
-                nearest_sub_idx = k
-
-        for k in range(len(subjects)):
-            if k != nearest_sub_idx:
-                continue
-            if k in seen_sub_idx:
-                for kk in range(len(ret)):
-                    if ret[kk]["sub_idx"] == k:
-                        ret[kk]["obj_bboxes"].append(
-                            {"bbox": objects[i]["bbox"], "lines": objects[i]["lines"], "index": objects[i]["index"]}
-                        )
-                        break
-            else:
-                ret.append(
-                    {
-                        "sub_bbox": {
-                            "bbox": subjects[k]["bbox"],
-                            "lines": subjects[k]["lines"],
-                            "index": subjects[k]["index"],
-                        },
-                        "obj_bboxes": [
-                            {"bbox": objects[i]["bbox"], "lines": objects[i]["lines"], "index": objects[i]["index"]}
-                        ],
-                        "sub_idx": k,
-                    }
+    def get_objects():
+        return reduct_overlap(
+            list(
+                map(
+                    lambda x: {"bbox": x["bbox"], "lines": x["lines"], "index": x["index"]},
+                    filter(
+                        lambda x: x["type"] == object_block_type,
+                        blocks,
+                    ),
                 )
-            seen_sub_idx.add(k)
-            seen_idx.add(k)
-
-    for i in range(len(subjects)):
-        if i in seen_sub_idx:
-            continue
-        ret.append(
-            {
-                "sub_bbox": {
-                    "bbox": subjects[i]["bbox"],
-                    "lines": subjects[i]["lines"],
-                    "index": subjects[i]["index"],
-                },
-                "obj_bboxes": [],
-                "sub_idx": i,
-            }
+            )
         )
 
-    return ret
+    # 调用通用方法
+    return tie_up_category_by_distance_v3(
+        get_subjects,
+        get_objects
+    )
 
 
 def get_type_blocks(blocks, block_type: Literal["image", "table"]):

mineru/model/mfr/unimernet/Unimernet.py

@@ -104,6 +104,10 @@ class UnimernetModel(object):
 
         # Create dataset with sorted images
         dataset = MathDataset(sorted_images, transform=self.model.transform)
+
+        # 如果batch_size > len(sorted_images)，则设置为不超过len(sorted_images)的2的幂
+        batch_size = min(batch_size, max(1, 2 ** (len(sorted_images).bit_length() - 1))) if sorted_images else 1
+
         dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=0)
 
         # Process batches and store results
@@ -115,7 +119,7 @@ class UnimernetModel(object):
                 mf_img = mf_img.to(dtype=self.model.dtype)
                 mf_img = mf_img.to(self.device)
                 with torch.no_grad():
-                    output = self.model.generate({"image": mf_img})
+                    output = self.model.generate({"image": mf_img}, batch_size=batch_size)
                 mfr_res.extend(output["fixed_str"])
 
                 # 更新进度条，每次增加batch_size，但要注意最后一个batch可能不足batch_size

mineru/model/mfr/unimernet/unimernet_hf/modeling_unimernet.py

@@ -468,7 +468,7 @@ class UnimernetModel(VisionEncoderDecoderModel):
         ).loss
         return {"loss": loss}
 
-    def generate(self, samples, do_sample: bool = False, temperature: float = 0.2, top_p: float = 0.95):
+    def generate(self, samples, do_sample: bool = False, temperature: float = 0.2, top_p: float = 0.95, batch_size=64):
         pixel_values = samples["image"]
         num_channels = pixel_values.shape[1]
         if num_channels == 1:
@@ -478,7 +478,13 @@ class UnimernetModel(VisionEncoderDecoderModel):
         if do_sample:
             kwargs["temperature"] = temperature
             kwargs["top_p"] = top_p
-        
+
+        if self.tokenizer.tokenizer.model_max_length > 1152:
+            if batch_size <= 32:
+                self.tokenizer.tokenizer.model_max_length = 1152  # 6g
+            else:
+                self.tokenizer.tokenizer.model_max_length = 1344  # 8g
+
         outputs = super().generate(
             pixel_values=pixel_values,
             max_new_tokens=self.tokenizer.tokenizer.model_max_length, # required

mineru/model/ocr/paddleocr2pytorch/pytorch_paddle.py

@@ -88,7 +88,7 @@ class PytorchPaddleOCR(TextSystem):
         kwargs['det_model_path'] = det_model_path
         kwargs['rec_model_path'] = rec_model_path
         kwargs['rec_char_dict_path'] = os.path.join(root_dir, 'pytorchocr', 'utils', 'resources', 'dict', dict_file)
-        # kwargs['rec_batch_num'] = 8
+        kwargs['rec_batch_num'] = 16
 
         kwargs['device'] = device
 

mineru/utils/magic_model_utils.py

@@ -0,0 +1,168 @@
+"""
+包含两个MagicModel类中重复使用的方法和逻辑
+"""
+from typing import List, Dict, Any, Callable
+from mineru.utils.boxbase import bbox_distance, is_in
+
+
+def reduct_overlap(bboxes: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """
+    去除重叠的bbox，保留不被其他bbox包含的bbox
+
+    Args:
+        bboxes: 包含bbox信息的字典列表
+
+    Returns:
+        去重后的bbox列表
+    """
+    N = len(bboxes)
+    keep = [True] * N
+    for i in range(N):
+        for j in range(N):
+            if i == j:
+                continue
+            if is_in(bboxes[i]['bbox'], bboxes[j]['bbox']):
+                keep[i] = False
+    return [bboxes[i] for i in range(N) if keep[i]]
+
+
+def tie_up_category_by_distance_v3(
+        get_subjects_func: Callable,
+        get_objects_func: Callable,
+        extract_subject_func: Callable = None,
+        extract_object_func: Callable = None
+):
+    """
+    通用的类别关联方法，用于将主体对象与客体对象进行关联
+
+    参数:
+        get_subjects_func: 函数，提取主体对象
+        get_objects_func: 函数，提取客体对象
+        extract_subject_func: 函数，自定义提取主体属性（默认使用bbox和其他属性）
+        extract_object_func: 函数，自定义提取客体属性（默认使用bbox和其他属性）
+
+    返回:
+        关联后的对象列表
+    """
+    subjects = get_subjects_func()
+    objects = get_objects_func()
+
+    # 如果没有提供自定义提取函数，使用默认函数
+    if extract_subject_func is None:
+        extract_subject_func = lambda x: x
+    if extract_object_func is None:
+        extract_object_func = lambda x: x
+
+    ret = []
+    N, M = len(subjects), len(objects)
+    subjects.sort(key=lambda x: x["bbox"][0] ** 2 + x["bbox"][1] ** 2)
+    objects.sort(key=lambda x: x["bbox"][0] ** 2 + x["bbox"][1] ** 2)
+
+    OBJ_IDX_OFFSET = 10000
+    SUB_BIT_KIND, OBJ_BIT_KIND = 0, 1
+
+    all_boxes_with_idx = [(i, SUB_BIT_KIND, sub["bbox"][0], sub["bbox"][1]) for i, sub in enumerate(subjects)] + [
+        (i + OBJ_IDX_OFFSET, OBJ_BIT_KIND, obj["bbox"][0], obj["bbox"][1]) for i, obj in enumerate(objects)
+    ]
+    seen_idx = set()
+    seen_sub_idx = set()
+
+    while N > len(seen_sub_idx):
+        candidates = []
+        for idx, kind, x0, y0 in all_boxes_with_idx:
+            if idx in seen_idx:
+                continue
+            candidates.append((idx, kind, x0, y0))
+
+        if len(candidates) == 0:
+            break
+        left_x = min([v[2] for v in candidates])
+        top_y = min([v[3] for v in candidates])
+
+        candidates.sort(key=lambda x: (x[2] - left_x) ** 2 + (x[3] - top_y) ** 2)
+
+        fst_idx, fst_kind, left_x, top_y = candidates[0]
+        fst_bbox = subjects[fst_idx]['bbox'] if fst_kind == SUB_BIT_KIND else objects[fst_idx - OBJ_IDX_OFFSET]['bbox']
+        candidates.sort(
+            key=lambda x: bbox_distance(fst_bbox, subjects[x[0]]['bbox']) if x[1] == SUB_BIT_KIND else bbox_distance(
+                fst_bbox, objects[x[0] - OBJ_IDX_OFFSET]['bbox']))
+        nxt = None
+
+        for i in range(1, len(candidates)):
+            if candidates[i][1] ^ fst_kind == 1:
+                nxt = candidates[i]
+                break
+        if nxt is None:
+            break
+
+        if fst_kind == SUB_BIT_KIND:
+            sub_idx, obj_idx = fst_idx, nxt[0] - OBJ_IDX_OFFSET
+        else:
+            sub_idx, obj_idx = nxt[0], fst_idx - OBJ_IDX_OFFSET
+
+        pair_dis = bbox_distance(subjects[sub_idx]["bbox"], objects[obj_idx]["bbox"])
+        nearest_dis = float("inf")
+        for i in range(N):
+            # 取消原先算法中 1对1 匹配的偏置
+            # if i in seen_idx or i == sub_idx:continue
+            nearest_dis = min(nearest_dis, bbox_distance(subjects[i]["bbox"], objects[obj_idx]["bbox"]))
+
+        if pair_dis >= 3 * nearest_dis:
+            seen_idx.add(sub_idx)
+            continue
+
+        seen_idx.add(sub_idx)
+        seen_idx.add(obj_idx + OBJ_IDX_OFFSET)
+        seen_sub_idx.add(sub_idx)
+
+        ret.append(
+            {
+                "sub_bbox": extract_subject_func(subjects[sub_idx]),
+                "obj_bboxes": [extract_object_func(objects[obj_idx])],
+                "sub_idx": sub_idx,
+            }
+        )
+
+    for i in range(len(objects)):
+        j = i + OBJ_IDX_OFFSET
+        if j in seen_idx:
+            continue
+        seen_idx.add(j)
+        nearest_dis, nearest_sub_idx = float("inf"), -1
+        for k in range(len(subjects)):
+            dis = bbox_distance(objects[i]["bbox"], subjects[k]["bbox"])
+            if dis < nearest_dis:
+                nearest_dis = dis
+                nearest_sub_idx = k
+
+        for k in range(len(subjects)):
+            if k != nearest_sub_idx:
+                continue
+            if k in seen_sub_idx:
+                for kk in range(len(ret)):
+                    if ret[kk]["sub_idx"] == k:
+                        ret[kk]["obj_bboxes"].append(extract_object_func(objects[i]))
+                        break
+            else:
+                ret.append(
+                    {
+                        "sub_bbox": extract_subject_func(subjects[k]),
+                        "obj_bboxes": [extract_object_func(objects[i])],
+                        "sub_idx": k,
+                    }
+                )
+            seen_sub_idx.add(k)
+            seen_idx.add(k)
+
+    for i in range(len(subjects)):
+        if i in seen_sub_idx:
+            continue
+        ret.append(
+            {
+                "sub_bbox": extract_subject_func(subjects[i]),
+                "obj_bboxes": [],
+                "sub_idx": i,
+            }
+        )
+
+    return ret

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.1.1"
+__version__ = "2.1.4"

pyproject.toml

@@ -109,8 +109,10 @@ pipeline_old_linux = [
 ]
 
 [project.urls]
-Home = "https://mineru.net/"
-Repository = "https://github.com/opendatalab/MinerU"
+homepage = "https://mineru.net/"
+documentation = "https://opendatalab.github.io/MinerU/"
+repository = "https://github.com/opendatalab/MinerU"
+issues = "https://github.com/opendatalab/MinerU/issues"
 
 [project.scripts]
 mineru = "mineru.cli:client.main"

signatures/version1/cla.json

@@ -391,6 +391,14 @@
       "created_at": "2025-07-16T08:53:24Z",
       "repoId": 765083837,
       "pullRequestNo": 3070
+    },
+    {
+      "name": "huazZeng",
+      "id": 125243371,
+      "comment_id": 3100630363,
+      "created_at": "2025-07-22T03:04:40Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3129
     }
   ]
 }