微信扫码
与创始人交个朋友
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,企业落地应用大模型首选服务商
产品:大模型应用平台+智能体定制开发+落地咨询服务
承诺:先做场景POC验证,看到效果再签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2024-09-19
一文彻底搞懂大模型 - Dify(Agent + RAG)
2024-09-19
Qwen2.5横空出世:从3B到72B,全面碾压同级对手
2024-09-19
突发!GPT-4o 级语音 Moshi 开源!
2024-09-19
Qwen2.5 全链路模型体验、下载、推理、微调、部署实战!
2024-09-19
通义千问Qwen2.5开源,媲美Llama3.1-405B
2024-09-19
Qwen 2.5 开源,API 打一折
2024-09-18
OpenAI o1的开源平替版self-replay RL来了!
2024-09-18
Y Combinator 投资的开源 Cursor 替代品来了!
2024-08-13
2024-05-06
2024-06-12
2023-07-01
2024-07-25
2024-07-08
2024-07-11
2024-07-18
2024-07-25
2024-06-16