FatalError: Segmentation fault is detected by the operating system.
#362
Comments
|
有尝试按照这个教程https://github.com/opendatalab/MinerU/blob/master/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md |
我的cuda和驱动版本如下： 提问：目前cuda版本和驱动版本不一致会影响该项目的正常运行嘛，因为是公用服务器，没办法换驱动版本。 |
|
驱动版本不一致没有太大问题，你这个问题是在教程中第9步还是第10步出现的？ |
刚刚测试了一下，设置cuda加速报错，如果是cpu没有问题。第9步报错，第10步也出现的问题。 下面是测试结果： demo: |
样本pdf可以上传一份到这里，我们调试一下，教程第九步就开始出现问题的话，说明系统不兼容，可能要搞个ubuntu22.04的docker试试 |
这里是我的几个测试用例，都是扫描版，包含纯文本、简单表格、复杂表格、图片等元素。另外文件都有页眉和水印，识别难度比较大。 |
我是按照https://github.com/opendatalab/MinerU/blob/master/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md来的，从第4步骤开始： 报错 不知道为什么
|
我是从第4步开始一步步来到第8步跑demo就出现这个错误，无论cpu还是cuda，都出现这个错误 |
报错的堆栈要完整上传一下 |
|
`(min) bigdata@gpu2 Miner $ magic-pdf pdf-command --pdf small_ocr.pdf sys.platform linux PyTorch built with:
[08/08 17:08:52 detectron2]: Command line arguments: {'config_file': '/home/bigdata/.conda/envs/min/lib/python3.10/site-packages/magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml', 'resume': False, 'eval_only': False, 'num_gpus': 1, 'num_machines': 1, 'machine_rank': 0, 'dist_url': 'tcp://127.0.0.1:57823', 'opts': ['MODEL.WEIGHTS', '/home/bigdata/projects/ysl/paint/Miner/PDF-Extract-Kit/models/Layout/model_final.pth']}
[08/08 17:08:54 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from /home/bigdata/projects/ysl/paint/Miner/PDF-Extract-Kit/models/Layout/model_final.pth ... C++ Traceback (most recent call last):0 at::_ops::conv2d::call(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::SymInt) Error Message Summary:FatalError: Segmentation fault (core dumped) |
如果是按照教程从第四步开始装的话，pytorch 不会是cu118的版本，正常教程安装pytorch 是cu121的，你这个真的有按教程安装吗？ |
|
这是正常的，因为在0.6.x版本中没有表格解析功能 |
我这边本地测试结果和在线效果一致，我把本地解析结果发你看下： 或者你也可以打包一下输出目录的所有文件，供我们分析。 |
我这边因cpu处理速度慢的原因只测试了 |
看了下中间过程文件，是有一些不应该出现的公式区域影响了解析效果，不清楚是不是依赖库版本不兼容导致的，如果可以的话，请运行pip list并上传结果供我们分析 |
` absl-py 2.1.0 |
|
我按照GPU文档里的第十条10. Enable CUDA Acceleration for OCR |
我是做了这一步安装paddlepaddle-gpu之后出现Segmentation fault (core dumped), #748 会是cuda版本不一致(118/121)的问题吗? |
Description of the bug | 错误描述
我在isseue看到了相似的问题，但他们的解决方式都不适合我。命令行运行报错。请大佬帮我看看。
magic-pdf == 0.6.2b1
How to reproduce the bug | 如何复现
1. 命令
magic-pdf pdf-command --pdf "testfile_1.pdf" --inside_model true2.日志
`2024-08-08 14:51:32.631 | WARNING | magic_pdf.cli.magicpdf:get_model_json:312 - not found json testfile_1.json existed
2024-08-08 14:51:32.631 | WARNING | magic_pdf.libs.config_reader:get_local_dir:64 - 'temp-output-dir' not found in magic-pdf.json, use '/tmp' as default
2024-08-08 14:51:32.798 | INFO | magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 1, cid_chars_radio: 0.0
2024-08-08 14:51:32.798 | WARNING | magic_pdf.filter.pdf_classify_by_type:classify:334 - pdf is not classified by area and text_len, by_image_area: False, by_text: False, by_avg_words: False, by_img_num: True, by_text_layout: False, by_img_narrow_strips: True, by_invalid_chars: True
INFO:datasets:PyTorch version 2.3.1 available.
2024-08-08 14:51:40.728 | INFO | magic_pdf.model.pdf_extract_kit:init:99 - DocAnalysis init, this may take some times. apply_layout: True, apply_formula: True, apply_ocr: True
2024-08-08 14:51:40.728 | INFO | magic_pdf.model.pdf_extract_kit:init:107 - using device: cuda
2024-08-08 14:51:40.729 | INFO | magic_pdf.model.pdf_extract_kit:init:109 - using models_dir: /root/.cache/modelscope/hub/wanderkid/PDF-Extract-Kit/models
CustomVisionEncoderDecoderModel init
CustomMBartForCausalLM init
CustomMBartDecoder init
[08/08 14:51:54 detectron2]: Rank of current process: 0. World size: 1
cuobjdump info : File '/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so' does not contain device code
[08/08 14:51:54 detectron2]: Environment info:
sys.platform linux
Python 3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0]
numpy 1.26.4
detectron2 0.6 @/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/detectron2
detectron2._C not built correctly: /lib/x86_64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found (required by /root/anaconda3/envs/MinerU/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so)
Compiler ($CXX) c++ (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
CUDA compiler Build cuda_11.8.r11.8/compiler.31833905_0
detectron2 arch flags /root/anaconda3/envs/MinerU/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so
DETECTRON2_ENV_MODULE
PyTorch 2.3.1+cu121 @/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/torch
PyTorch debug build False
torch._C._GLIBCXX_USE_CXX11_ABI False
GPU available Yes
GPU 0,1,2,3 NVIDIA GeForce RTX 3090 (arch=8.6)
CUDA_HOME /usr/local/cuda
Pillow 10.4.0
torchvision 0.18.1+cu121 @/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/torchvision
torchvision arch flags 5.0, 6.0, 7.0, 7.5, 8.0, 8.6, 9.0
fvcore 0.1.5.post20221221
iopath 0.1.9
cv2 4.6.0
PyTorch built with:
[08/08 14:51:54 detectron2]: Command line arguments: {'config_file': '/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml', 'resume': False, 'eval_only': False, 'num_gpus': 1, 'num_machines': 1, 'machine_rank': 0, 'dist_url': 'tcp://127.0.0.1:57823', 'opts': ['MODEL.WEIGHTS', '/root/.cache/modelscope/hub/wanderkid/PDF-Extract-Kit/models/Layout/model_final.pth']}
[08/08 14:51:54 detectron2]: Contents of args.config_file=/root/anaconda3/envs/MinerU/lib/python3.10/site-packages/magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml:
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:
TRAIN:
GLOBAL:
HACK: 1.0
ICDAR_DATA_DIR_TEST: ''
ICDAR_DATA_DIR_TRAIN: ''
INPUT:
CROP:
ENABLED: true
SIZE:
TYPE: absolute_range
FORMAT: RGB
MASK_FORMAT: polygon
MAX_SIZE_TEST: 1333
MAX_SIZE_TRAIN: 1333
MIN_SIZE_TEST: 800
MIN_SIZE_TRAIN:
MIN_SIZE_TRAIN_SAMPLING: choice
RANDOM_FLIP: horizontal
MODEL:
ANCHOR_GENERATOR:
ANGLES:
ASPECT_RATIOS:
NAME: DefaultAnchorGenerator
OFFSET: 0.0
SIZES:
BACKBONE:
FREEZE_AT: 2
NAME: build_vit_fpn_backbone
CONFIG_PATH: ''
DEVICE: cuda
FPN:
FUSE_TYPE: sum
IN_FEATURES:
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:
PIXEL_STD:
PROPOSAL_GENERATOR:
MIN_SIZE: 0
NAME: RPN
RESNETS:
DEFORM_MODULATED: false
DEFORM_NUM_GROUPS: 1
DEFORM_ON_PER_STAGE:
DEPTH: 50
NORM: FrozenBN
NUM_GROUPS: 1
OUT_FEATURES:
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:
FOCAL_LOSS_ALPHA: 0.25
FOCAL_LOSS_GAMMA: 2.0
IN_FEATURES:
IOU_LABELS:
IOU_THRESHOLDS:
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:
IOUS:
ROI_BOX_HEAD:
BBOX_REG_LOSS_TYPE: smooth_l1
BBOX_REG_LOSS_WEIGHT: 1.0
BBOX_REG_WEIGHTS:
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:
IOU_LABELS:
IOU_THRESHOLDS:
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:
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:
BOUNDARY_THRESH: -1
CONV_DIMS:
HEAD_NAME: StandardRPNHead
IN_FEATURES:
IOU_LABELS:
IOU_THRESHOLDS:
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:
LOSS_WEIGHT: 1.0
NAME: SemSegFPNHead
NORM: GN
NUM_CLASSES: 10
VIT:
DROP_PATH: 0.1
IMG_SIZE:
NAME: layoutlmv3_base
OUT_FEATURES:
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:
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:
DETECTIONS_PER_IMAGE: 100
EVAL_PERIOD: 1000
EXPECTED_RESULTS: []
KEYPOINT_OKS_SIGMAS: []
PRECISE_BN:
ENABLED: false
NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0
[08/08 14:51:56 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from /root/.cache/modelscope/hub/wanderkid/PDF-Extract-Kit/models/Layout/model_final.pth ...
[08/08 14:51:56 fvcore.common.checkpoint]: [Checkpointer] Loading from /root/.cache/modelscope/hub/wanderkid/PDF-Extract-Kit/models/Layout/model_final.pth ...
2024-08-08 14:51:57.268 | INFO | magic_pdf.model.pdf_extract_kit:init:132 - DocAnalysis init done!
2024-08-08 14:51:57.268 | INFO | magic_pdf.model.doc_analyze_by_custom_model:custom_model_init:92 - model init cost: 24.469878435134888`
3.Traceback
`--------------------------------------
C++ Traceback (most recent call last):
0 at::_ops::conv2d::call(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::SymInt)
1 at::native::conv2d_symint(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::SymInt)
2 at::_ops::convolution::call(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, bool, c10::ArrayRefc10::SymInt, c10::SymInt)
3 at::_ops::convolution::redispatch(c10::DispatchKeySet, at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, bool, c10::ArrayRefc10::SymInt, c10::SymInt)
4 at::native::convolution(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, bool, c10::ArrayRef, long)
5 at::_ops::_convolution::call(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, bool, c10::ArrayRefc10::SymInt, c10::SymInt, bool, bool, bool, bool)
6 at::native::_convolution(at::Tensor const&, at::Tensor const&, std::optionalat::Tensor const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, bool, c10::ArrayRef, long, bool, bool, bool, bool)
7 at::_ops::cudnn_convolution::call(at::Tensor const&, at::Tensor const&, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::ArrayRefc10::SymInt, c10::SymInt, bool, bool, bool)
8 at::native::cudnn_convolution(at::Tensor const&, at::Tensor const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, long, bool, bool, bool)
Error Message Summary:
FatalError:
Segmentation faultis detected by the operating system.[TimeInfo: *** Aborted at 1723099917 (unix time) try "date -d @1723099917" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x59) received by PID 37094 (TID 0x7f617e0133c0) from PID 89 ***]
Segmentation fault`
Operating system | 操作系统
Linux
Python version | Python 版本
3.10
Software version | 软件版本 (magic-pdf --version)
0.6.x
Device mode | 设备模式
cuda
The text was updated successfully, but these errors were encountered: