Ucas-HaoranWei/GOT-OCR2.0
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Python
Issues
- 0
latex output instead of mathpix
#279 opened by devops724 - 0
可以输出文本对应的位置标定吗?
#278 opened by oushu1zhangxiangxuan1 - 0
群二维码过期了
#277 opened by oushu1zhangxiangxuan1 - 1
请问latex这块儿数据集用的是哪个呢?想单独针对这个场景ft优化下
#274 opened by xsank - 1
请问对于上下行文字存在粘连的如何调整才能进行识别呢
#276 opened by Giserlei123 - 1
OpenVINO for GOT
#275 opened by can-gaa-hou - 3
请问能否将pdf导入到ocr进行扫描呢?
#273 opened by aqiuX17 - 3
第一行文字会被识别为标题
#242 opened by jiandandema - 1
- 4
- 2
Open source GGUF and Llama.cpp inference
#266 opened by MosRat - 0
Docker and web api to using it
#271 opened by gamersalpha - 1
- 0
Image cropping inquiry
#270 opened by cryingjin - 0
- 3
七群也需要成员邀请,请问如何加入?
#267 opened by lihui52 - 1
为什么box先归一化再乘上1000
#268 opened by GuoQuanhao - 0
- 0
是否有微调的演示小数据集
#264 opened by monkeycc - 0
Bounding boxes of the text detected and layout detection
#263 opened by ep0p - 0
怎么获取每个字符的坐标和准确率?
#262 opened by nissansz - 0
https://huggingface.co/spaces/stepfun-ai/GOT_official_online_demo 好像没法识别韩文,有支持其它语种的模型吗?
#261 opened by nissansz - 0
plain multi-crop OCR这种模式如何配置
#259 opened by fastdebuger - 1
基于GOT-OCR2.0做视觉信息抽取
#254 opened by ignore1999 - 1
参数位置是否传反了
#258 opened by qazwsx74269 - 2
Recognize matrices as chemical expressions
#249 opened by junjiemao - 7
Stage-1 batchsize>4 CUDA out of memory
#240 opened by Niujunbo2002 - 2
why did not compare with generalist models, including GPT-4o, Gemini-1.5, Claude-3.5- Sonnet, Qwen2-VL-72B, and InternVL2
#257 opened by guangdongliang - 1
- 0
使用模型train失败
#255 opened by lifejwang11 - 14
七群wx二维码失效了,能再发一个吗
#230 opened by micrazy - 0
Is there a step-by-step instruction for training the model for the Arabic language?
#253 opened by AboulfazlSeilsepour - 0
是否可以自定义数字参数
#252 opened by monkeycc - 0
- 0
- 2
按照官网文档执行这条命令报错:pip install -e .
#241 opened by freezehe - 1
GOT-OCR2_0 is supported in PaddleMIX by Paddle Team
#247 opened by luyao-cv - 0
微调后模型推理自定义数据集方式
#232 opened by katie312 - 0
Val 資料集
#245 opened by claineycku - 0
请问可以限制模型预测时的显存上限吗?
#244 opened by 4majesty - 2
- 6
- 2
model is taking long inference time after training, can i reduce it? have you any idea about it?
#243 opened by rahulverma7788 - 2
单页PDF解析需要将近20秒,有没有推理加速的方案?比如vllm或者lmdeploy
#236 opened by FanWan - 1
图片上没有文字,需要输出 "",但是现在会输出一些错误的信息
#235 opened by xiaolongc929 - 1
Pre-training Vision encoder
#229 opened by cryingjin - 0
Asking about dataset preparing
#237 opened by tadkt - 0
insights on noise in got dataset and fine-tuning issues
#234 opened by ep0p - 1
Format类型的输出到底是一种什么格式,该如何转换成Latex
#233 opened by Elton-Yang - 2
视觉的编码模块显存消耗过大的问题?
#231 opened by QiusongYang