PaddleOCR
PaddleOCR copied to clipboard
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and de...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:arm32/64 物联网设备(没啥高配置) ----- 有大佬实现轻量化的解决方案么?有没有2GB边缘设备能跑ocr预测? docker pull paddlepaddle/fastdeploy 4GB? 实际大概12GB...直接劝退 docker pull paddlepaddle/serving 1.44GB 实际大概需要4GB 没有1GB一下的CPU部署方案?求教..
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:Linux version 3.10.0-514.el7.x86_64 ([email protected]) (gcc version 4.8.5 20150623 (Red Hat 4.8.5-11) (GCC) ) - 版本号/Version:Paddle:`2.4.2`,PaddleOCR:`2.7.0.3`,问题相关组件/Related components: - 运行指令/Command...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:Linux - 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:2.7 - 运行指令/Command Code:paddleocr --image_dir 2023-09-26-11-04-19.png --use_angle_cls false --use_gpu true --rec false --det_algorithm="DB"...
# 现状 PaddleOCR依赖了两个requirements.txt,分别是根目录下的 requirement.txt 和 ppstructure/recovery/requirements.txt,过多未标明版本的依赖项会导致依赖混乱。本ISSUE以Paddle v2.6和 requirement.txt 中的信息,对PaddleOCR当前的依赖情况进行梳理,并给出优化建议。 更多相关信息参考 [PaddleOCR疑难解决](https://github.com/PaddlePaddle/PaddleOCR/issues/11906)。 # 依赖信息 |包名称|功能|调用说明/提供的功能|建议| |--|--|--|--| |shapely|用于对象几何操作的2D几何库。支持多种几何对象的创建和操作|LineString, Point, Polygon|| |scikit-image|图像处理|thin、random_noise|| |imgaug|图像增强库|augmenters、Keypoint、KeypointsOnImage|| |pyclipper|2D裁剪库|PyclipperOffset、JT_ROUND、ET_CLOSEDPOLYGON| |lmdb|轻量级的磁盘键值存储数据库|为LMDBDataSetTableMaster提供支持|调用语句仅env = lmdb.open(...)| |tqdm|显示长循环的进度||| |numpy|数学运算||| |visualdl|可视化深度学习训练过程的工具|LogWriter|使用位置较少,可以移除| |rapidfuzz|字符串相似度匹配|Levenshtein|| |opencv-python=1.13, 2.0支持的活动。
为什么同样一张图片,在调用高精度识别模型之后,需要5分钟左右得出最后的结果,而超轻量模型只需不到20秒,速度差别这么大吗
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:20.04.1-Ubuntu - 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:ppstructure - 运行指令/Command Code: design_pic_engine = PPStructure(table=False, ocr=False, show_log=True, use_gpu=False, layout_model_dir='./output_inference/picodet_s_320_coco_lcnet') result =...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem The code will not work with `numpy>=1.24` Reference for the deprecation: https://numpy.org/devdocs/release/1.20.0-notes.html#using-the-aliases-of-builtin-types-like-np-int-is-deprecated When using `paddleocr` with the previous `numpy` versions...
System Environment: Windows 11, Python 3.9.9 Version: Paddle 2.7+ PaddleOCR I trained a recognition model using the configuration file config.yml and obtained excellent results on my dataset. However, after exporting...
Have been trying to compile libpaddle_inference.so on Ubuntu 20 without success. Used cmake .. -DWITH_CONTRIB=OFF -DWITH_MKL=ON -DWITH_MKLDNN=ON -DWITH_TESTING=OFF -DCMAKE_BUILD_TYPE=Release -DWITH_INFERENCE_API_TEST=OFF -DON_INFER=ON -DWITH_PYTHON=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda-12.4/bin/nvcc -DWITH_GPU=ON -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-12.4 Error is Command-line error: invalid...