magic-pdf, version 0.8.1 pdf 解析报错

[wertyac]

Description of the bug | 错误描述

python =3.10 安装方式遵循doc文档。 CUDA version为11.8 Ubuntu 为22.04. 报如下错误，无法解析成功。 2024-10-18 09:32:53.186 | ERROR | magic_pdf.tools.cli:parse_doc:96 - Coordinate 'right' is less than 'left'

How to reproduce the bug | 如何复现

(mineru) health@222server:~$ magic-pdf -p small_ocr.pdf -o /home/health/pdf/ 2024-10-18 09:29:54.551	INFO	magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 8, cid_chars_radio: 0.0 2024-10-18 09:29:54.553	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: False, by_invalid_chars: True 2024-10-18 09:30:02.736	INFO	magic_pdf.model.pdf_extract_kit:init:180 - DocAnalysis init, this may take some times. apply_layout: True, apply_formula: True, apply_ocr: True, apply_table: False 2024-10-18 09:30:02.736	INFO	magic_pdf.model.pdf_extract_kit:init:188 - using device: cuda 2024-10-18 09:30:02.736	INFO	magic_pdf.model.pdf_extract_kit:init:190 - using models_dir: /home/health/.cache/modelscope/hub/opendatalab/PDF-Extract-Kit/models CustomVisionEncoderDecoderModel init CustomMBartForCausalLM init CustomMBartDecoder init [10/18 09:30:19 detectron2]: Rank of current process: 0. World size: 1 [10/18 09:30:19 detectron2]: Environment info:

sys.platform linux Python 3.10.15 (main, Oct 3 2024, 07:27:34) [GCC 11.2.0] numpy 1.26.4 detectron2 0.6 @/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/detectron2 Compiler GCC 11.4 CUDA compiler not available DETECTRON2_ENV_MODULE PyTorch 2.3.1+cu121 @/home/health/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 NVIDIA GeForce RTX 4070 (arch=8.9) Driver version 535.183.01 CUDA_HOME /usr/local/cuda-11.8 Pillow 11.0.0 torchvision 0.18.1+cu121 @/home/health/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:

• GCC 9.3
• C++ Version: 201703
• Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• LAPACK is enabled (usually provided by MKL)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 12.1
• NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
• CuDNN 8.6 (built against CUDA 11.8)
  • Built with CuDNN 8.9.2
• Magma 2.6.1
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

[10/18 09:30:19 detectron2]: Command line arguments: {'config_file': '/home/health/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', '/home/health/.cache/modelscope/hub/opendatalab/PDF-Extract-Kit/models/Layout/model_final.pth']} [10/18 09:30:19 detectron2]: Contents of args.config_file=/home/health/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:

• 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

[10/18 09:30:21 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from /home/health/.cache/modelscope/hub/opendatalab/PDF-Extract-Kit/models/Layout/model_final.pth ... [10/18 09:30:21 fvcore.common.checkpoint]: [Checkpointer] Loading from /home/health/.cache/modelscope/hub/opendatalab/PDF-Extract-Kit/models/Layout/model_final.pth ... 2024-10-18 09:30:22.596 | INFO | magic_pdf.model.pdf_extract_kit:init:248 - DocAnalysis init done! 2024-10-18 09:30:22.596 | INFO | magic_pdf.model.doc_analyze_by_custom_model:custom_model_init:98 - model init cost: 28.04293656349182 2024-10-18 09:30:24.960 | INFO | magic_pdf.model.pdf_extract_kit:call:259 - layout detection cost: 1.47

0: 1888x1312 219 embeddings, 81 isolateds, 106.1ms Speed: 18.1ms preprocess, 106.1ms inference, 42.8ms postprocess per image at shape (1, 3, 1888, 1312) 2024-10-18 09:32:48.691 | INFO | magic_pdf.model.pdf_extract_kit:call:289 - formula nums: 300, mfr time: 132.87 2024-10-18 09:32:52.197 | INFO | magic_pdf.model.pdf_extract_kit:call:372 - ocr cost: 3.47 2024-10-18 09:32:52.901 | INFO | magic_pdf.model.pdf_extract_kit:call:259 - layout detection cost: 0.7

0: 1888x1312 290 embeddings, 10 isolateds, 105.5ms Speed: 18.2ms preprocess, 105.5ms inference, 125.3ms postprocess per image at shape (1, 3, 1888, 1312) 2024-10-18 09:32:53.186 | ERROR | magic_pdf.tools.cli:parse_doc:96 - Coordinate 'right' is less than 'left' Traceback (most recent call last):

File "/home/health/anaconda3/envs/mineru/bin/magic-pdf", line 8, in sys.exit(cli()) │ │ └ │ └ └ <module 'sys' (built-in)> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/click/core.py", line 1157, in call return self.main(args, kwargs) │ │ │ └ {} │ │ └ () │ └ <function BaseCommand.main at 0x7e1eebe32950> └ File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) │ │ └ <click.core.Context object at 0x7e1eec00c880> │ └ <function Command.invoke at 0x7e1eebe33400> └ File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, ctx.params) │ │ │ │ │ └ {'path': 'small_ocr.pdf', 'output_dir': '/home/health/pdf/', 'method': 'auto', 'debug_able': False, 'start_pageid': 0, 'end... │ │ │ │ └ <click.core.Context object at 0x7e1eec00c880> │ │ │ └ <function cli at 0x7e1db96d53f0> │ │ └ │ └ <function Context.invoke at 0x7e1eebe32170> └ <click.core.Context object at 0x7e1eec00c880> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/click/core.py", line 783, in invoke return __callback(args, **kwargs) │ └ {'path': 'small_ocr.pdf', 'output_dir': '/home/health/pdf/', 'method': 'auto', 'debug_able': False, 'start_pageid': 0, 'end... └ () File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/tools/cli.py", line 102, in cli parse_doc(path) │ └ 'small_ocr.pdf' └ <function cli..parse_doc at 0x7e1eec0337f0>

File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/tools/cli.py", line 84, in parse_doc do_parse( └ <function do_parse at 0x7e1db96d4b80> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/tools/common.py", line 79, in do_parse pipe.pipe_analyze() │ └ <function UNIPipe.pipe_analyze at 0x7e1db96d4d30> └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x7e1db96ba770> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/pipe/UNIPipe.py", line 33, in pipe_analyze self.model_list = doc_analyze(self.pdf_bytes, ocr=True, │ │ │ │ └ b'%PDF-1.7\r\n%\xa1\xb3\xc5\xd7\r\n1 0 obj\r\n<</Pages 2 0 R /Type/Catalog>>\r\nendobj\r\n2 0 obj\r\n<</Count 8/Kids[ 4 0 R ... │ │ │ └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x7e1db96ba770> │ │ └ <function doc_analyze at 0x7e1e5a4b95a0> │ └ [] └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x7e1db96ba770> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/model/doc_analyze_by_custom_model.py", line 129, in doc_analyze result = custom_model(img) │ └ array([[[255, 255, 255], │ [255, 255, 255], │ [255, 255, 255], │ ..., │ [255, 255, 255], │ [255... └ <magic_pdf.model.pdf_extract_kit.CustomPEKModel object at 0x7e1db91afe50> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/model/pdf_extract_kit.py", line 274, in call bbox_img = get_croped_image(Image.fromarray(image), [xmin, ymin, xmax, ymax]) │ │ │ │ │ │ │ └ 0 │ │ │ │ │ │ └ 2361 │ │ │ │ │ └ 88 │ │ │ │ └ 2491 │ │ │ └ array([[[255, 255, 255], │ │ │ [255, 255, 255], │ │ │ [255, 255, 255], │ │ │ ..., │ │ │ [255, 255, 255], │ │ │ [255... │ │ └ <function fromarray at 0x7e1cfd945900> │ └ <module 'PIL.Image' from '/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/PIL/Image.py'> └ <function get_croped_image at 0x7e1cebd8f250> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/magic_pdf/model/pek_sub_modules/post_process.py", line 16, in get_croped_image croped_img = image_pil.crop((x_min, y_min, x_max, y_max)) │ │ │ │ │ └ 0 │ │ │ │ └ 2361 │ │ │ └ 88 │ │ └ 2491 │ └ <function Image.crop at 0x7e1cfd90bac0> └ <PIL.Image.Image image mode=RGB size=3405x5000 at 0x7E1CD1172AA0> File "/home/health/anaconda3/envs/mineru/lib/python3.10/site-packages/PIL/Image.py", line 1305, in crop raise ValueError(msg) └ "Coordinate 'right' is less than 'left'"

ValueError: Coordinate 'right' is less than 'left'

Operating system | 操作系统

Linux

Python version | Python 版本

3.10

Software version | 软件版本 (magic-pdf --version)

0.8.x

Device mode | 设备模式

cuda

[myhloli]

从0: 1888x1312 219 embeddings, 81 isolateds, 106.1ms Speed: 18.1ms preprocess, 106.1ms inference, 42.8ms postprocess per image at shape (1, 3, 1888, 1312) 2024-10-18 09:32:48.691 | INFO | magic_pdf.model.pdf_extract_kit:call:289 - formula nums: 300, mfr time: 132.87 这个日志来看的话，应该是安装时网络波动导致pytorch没有装好，运行时在mfd环境虚空产生了很多虚假的公式bbox。

建议使用网速较好的设备，以及镜像源的方式，减少安装过程中的不确定因素。

[wertyac]

从0: 1888x1312 219 embeddings, 81 isolateds, 106.1ms Speed: 18.1ms preprocess, 106.1ms inference, 42.8ms postprocess per image at shape (1, 3, 1888, 1312) 2024-10-18 09:32:48.691 | INFO | magic_pdf.model.pdf_extract_kit:call:289 - formula nums: 300, mfr time: 132.87 这个日志来看的话，应该是安装时网络波动导致pytorch没有装好，运行时在mfd环境虚空产生了很多虚假的公式bbox。

建议使用网速较好的设备，以及镜像源的方式，减少安装过程中的不确定因素。

谢谢我重新安装一下试试，会不会和cuda和cudnn版本有关系？cuda用的是11.8.

[myhloli]

pytorch会使用pip安装cu12.1作为依赖，不会使用系统的cu11.8

[wertyac]

pytorch会使用pip安装cu12.1作为依赖，不会使用系统的cu11.8

奇怪，我换了一条服务器，ubuntu 22.04， CUDA 12.1， driver 550.120 python 3.10 同样的安装方案，这个不会报错。。。。太奇怪了。