微信扫码
添加专属顾问
我要投稿
pip install magic-pdf
cp magic-pdf.template.json ~/magic-pdf.json
magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"
图像
,表格
,标题
,文本
等;行内公式
和行间公式
;conda create -n pdfpipeline python=3.10
git clone https://github.com/opendatalab/PDF-Extract-Kit.git
pip3 install -r requirements+cpu.txt
pip install https://github.com/opendatalab/PDF-Extract-Kit/raw/main/assets/whl/detectron2-0.6-cp310-cp310-macosx_11_0_arm64.whl
PDF-Extract-Kit/configs/model_configs.yaml:2
PDF-Extract-Kit/modules/layoutlmv3/layoutlmv3_base_inference.yaml:72
git lfs clone https://huggingface.co/wanderkid/PDF-Extract-Kit
python pdf_extract.py --pdf data/pdfs/ocr_1.pdf
File "/Users/linyu/ai/PDF-Extract-Kit/modules/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py", line 71, in forward
position_embedding = F.interpolate(position_embedding, size=(Hp, Wp), mode='bicubic')
NotImplementedError: The operator 'aten::upsample_bicubic2d.out' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on https://github.com/pytorch/pytorch/issues/77764. As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.
export PYTORCH_ENABLE_MPS_FALLBACK=1
或者在py 运行文件中加import os
os.environ['PYTORCH_ENABLE_MPS_FALLBACK'] = '1'
RuntimeError: Expected repeatBuffer && cumsumBuffer && resultBuffer to be true, but got false.
magic-pdf pdf-command --pdf "/Users/linyu/ai/pdf储能政策知识库/《“十四五”能源领域科技创新规划》2021.pdf" --model ""
53AI,企业落地大模型首选服务商
产品:场景落地咨询+大模型应用平台+行业解决方案
承诺:免费POC验证,效果达标后再合作。零风险落地应用大模型,已交付160+中大型企业
2025-09-04
K8s部署Dify从0到1:最佳实践与避坑指南
2025-09-04
国内本地部署Gemini CLI,苹果电脑更丝滑,开发者彻底狂欢
2025-09-04
快手开源Keye-VL1.5:8B多模态模型细节揭秘,短视频理解很强!
2025-09-04
美团也开源了大模型,但我觉得他们的野心是通用生活Agent。
2025-09-04
重大福利!OpenAI免费开放ChatGPT Projects,3大功能太香了
2025-09-03
10分钟零代码,0元立即部署OpenAI开源模型 GPT-OSS
2025-09-03
coze开源能力及与官方闭源版比较
2025-09-03
工业级AI平台开源,识别率超过99%,包含图像采集、智能检测、数据标注、模型训练四大模块
2025-07-23
2025-06-17
2025-08-20
2025-06-17
2025-07-23
2025-08-05
2025-07-14
2025-08-20
2025-07-29
2025-07-12
2025-09-01
2025-08-16
2025-08-13
2025-08-11
2025-08-11
2025-08-06
2025-08-06
2025-08-06