Wang Xin comments

Results 252 comments of


                                            Wang Xin

PPOCRLabel 报错

这可能是由于 paddlepaddle 2.6 在 non avx512 有问题导致的 - https://github.com/PaddlePaddle/PaddleOCR/issues/11597 develop分支已修复 - https://github.com/PaddlePaddle/Paddle/pull/64132/

Error with pyclipper inhomogeneous expanded array

It works. ```shell paddleocr --image_dir doc/imgs/1.jpg ``` ``` [2024/05/18 09:05:33] ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=False, use_xpu=False, use_npu=False, use_mlu=False, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, gpu_id=0, image_dir='doc/imgs/1.jpg', page_num=0, det_algorithm='DB', det_model_dir='/Users/wangxin/.paddleocr/whl/det/ch/ch_PP-OCRv4_det_infer', det_limit_side_len=960, det_limit_type='max', det_box_type='quad',...

cffi.VerificationError: CompileError: command '/usr/bin/clang' failed with exit code 1

用的python版本是多少

cffi.VerificationError: CompileError: command '/usr/bin/clang' failed with exit code 1

please refer: - https://github.com/longcw/yolo2-pytorch/issues/55 - https://github.com/jwyang/faster-rcnn.pytorch/issues/641 估计是gcc或者clang不在环境里

RecursionError: maximum recursion depth exceeded in comparison

看着像字典没用对

table_master 模型八位格式坐标decode问题

@plotnine1219 是否愿意提一个PR修复来这个问题

added sliding window for large image inference

hi @aspaul20, maybe you need to add the post-processing part as well to avoid individual words being separated.

added sliding window for large image inference

I haven't tested it yet, I'm more curious if this fix is valid for the following picture? ![2405 04788v1_1](https://github.com/PaddlePaddle/PaddleOCR/assets/17264618/549c8c31-68ad-4176-92ca-4d8d63133974)