Skip to content

Issues: Topdu/OpenOCR

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
35 Open 14 Closed
35 Open 14 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Will you train a paddle model to include Chinese (Simplified and Traditional), Japanese, Korean and English?
#28 opened Nov 7, 2024 by nissansz
RecursionError: maximum recursion depth exceeded while calling a Python object
#7 opened Jul 19, 2024 by XXmm-s
6
Training with PyTorch is significantly slower than with PaddleOCR
#9 opened Aug 4, 2024 by gaozhun
19
Thank you for the amazing work. Waiting for the release of the svtrv2 paper
#13 opened Aug 12, 2024 by EasyIsAllYouNeed
1
Great!
#14 opened Aug 14, 2024 by Henryplay
1
RecursionError: maximum recursion depth exceeded in comparison
#16 opened Sep 2, 2024 by hp0716
12
请问配置文件里的图片尺寸可以根据自己的图片进行修改吗？
#17 opened Sep 9, 2024 by hp0716
1
请问有基础的教程吗？
#19 opened Sep 26, 2024 by xuanch0034
2
optimize ctc focal loss compute stability
#20 opened Oct 8, 2024 by liwenju0
2
paddleocr 2.9.1 rec_svtrv2_ch.yml 这个配置文件需要什么系统什么版本的paddle才能训练？需要多大显存？目前训练ResNet34模型没问题，一改这个配置文件就爆显存，或者自动退出训练
#23 opened Oct 26, 2024 by nissansz
26
Scripts for downloading datasets?
#24 opened Oct 31, 2024 by ir2718
5
How to determine if the best model is achieved? Is it necessary to change default lr when resuming traning?
#26 opened Nov 4, 2024 by nissansz
Hi, Great work and Repo, any plans to support recognition model evaluation for long sentences?
#1 opened May 31, 2024 by bely66
7
If I want to train one epoch only, how to set lr?
#27 opened Nov 6, 2024 by nissansz
3
If I randomly generate image for each line during training, what is the best lr and other parameters to set?
#29 opened Nov 11, 2024 by nissansz
When training the Chinese benchmark dataset with svtrv2_ctc, the loss drops to 64 and cannot go lower. How to resolve this?
#31 opened Nov 20, 2024 by AnkhXXX
9
能否公开下预训练的三个模型（mobile/server rec /DBNet det）的数据集和训练参数？
#40 opened Nov 27, 2024 by xiaozhubenben
2
bpe_simple_vocab_16e6.txt.gz'
#48 opened Dec 3, 2024 by tengxniu
3
No module named 'tools.infer_e2e'
#54 opened Dec 6, 2024 by daisy-disc
1
How can the recognition model export in onnx format support variable length? The training size is 32 * 128, and using onnx model to predict other size formats may cause errors, such as 32 * 256 or 32 * X, where position encoding has been disabled
#60 opened Dec 11, 2024 by dlml
1
修改识别文本长度
#61 opened Dec 13, 2024 by wzg722
1
npu deploy
#63 opened Dec 17, 2024 by han508
1
predict txt is different between eval_rec.py and infer_rec.py
#65 opened Dec 18, 2024 by maxh2010
5
support Fine-tunes ?
#66 opened Dec 20, 2024 by dashi19880521
2
svtrv2-s的模型结构不一致
#79 opened Jan 9, 2025 by tengxniu
ProTip! Mix and match filters to narrow down what you’re looking for.