Replies: 2 comments
-
根据您提供的训练日志对比,我建议不要在训练初期就加入疑难近似字符。原因如下:
这样的渐进式训练策略可以帮助模型更好地学习处理疑难近似字符,同时保持对基础字符的良好识别能力。 Response generated by feifei-bot | claude-3-5-sonnet-latest |
Beta Was this translation helpful? Give feedback.
0 replies
-
如果在预训练的svtr2模型上改变字典,增加到几万个字符,恢复训练,
与全新训练几万个字符,哪种效果会好?
…--------------------------------------------------------------------------------
------------------ 原始邮件 ------------------
发件人: Wang Xin ***@***.***>
发送时间: 2025-01-10 09:40:01
收件人:PaddlePaddle/PaddleOCR ***@***.***>
抄送:nissanjp ***@***.***>,Author ***@***.***>
主题: Re: [PaddlePaddle/PaddleOCR] svtr2 疑难近似字符应该在什么时候加入训练? (Discussion #14523)
根据您提供的训练日志对比,我建议不要在训练初期就加入疑难近似字符。原因如下:
从训练效果来看: 不加入疑难近似字符时:acc达到0.5641,norm_edit_dis达到0.8391 加入15%疑难近似字符后:acc下降到0.3422,norm_edit_dis下降到0.6666 建议的加入时机: 建议在模型基本收敛,识别准确率相对稳定后再逐步加入疑难近似字符 可以采用渐进式方式:先用基础字符训练至一定准确率→再少量引入疑难字符(如5%)→观察效果后再逐步增加比例 避免一次性加入过多(如15%)疑难字符,这样可能会导致模型难以收敛 具体建议: 先用基础字符训练直到acc稳定在0.6以上 每次只增加约5%的疑难近似字符 每次加入新字符后,给予充分的训练轮次让模型适应 观察验证集指标变化,如果指标下降明显则适当调整策略 这样的渐进式训练策略可以帮助模型更好地学习处理疑难近似字符,同时保持对基础字符的良好识别能力。
Response generated by feifei-bot | claude-3-5-sonnet-latest
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
svtr2 疑难近似字符应该在什么时候加入训练?
加入疑难近似字符前日志如下
[2025/01/10 08:46:42] ppocr INFO: epoch: [1/50], global_step: 800, lr: 0.000001, CTCLoss: 14.587288, NRTRLoss: 2.853578, loss: 18.047794, avg_reader_cost: 0.00208 s, avg_batch_cost: 0.18747 s, avg_samples: 2.35, ips: 12.53550 samples/s, eta: 26 days, 8:36:20, max_mem_reserved: 2097 MB, max_mem_allocated: 1821 MB
[2025/01/10 08:47:01] ppocr INFO: epoch: [1/50], global_step: 900, lr: 0.000001, CTCLoss: 28.381334, NRTRLoss: 3.626843, loss: 32.118370, avg_reader_cost: 0.00200 s, avg_batch_cost: 0.17118 s, avg_samples: 2.22, ips: 12.96876 samples/s, eta: 25 days, 23:04:52, max_mem_reserved: 2097 MB, max_mem_allocated: 1821 MB
[2025/01/10 08:47:19] ppocr INFO: epoch: [1/50], global_step: 1000, lr: 0.000001, CTCLoss: 18.424065, NRTRLoss: 2.977797, loss: 21.543367, avg_reader_cost: 0.00181 s, avg_batch_cost: 0.17177 s, avg_samples: 2.41, ips: 14.03078 samples/s, eta: 25 days, 15:38:51, max_mem_reserved: 2097 MB, max_mem_allocated: 1821 MB
[2025/01/10 08:48:30] ppocr INFO: cur metric, acc: 0.5641729542609956, norm_edit_dis: 0.8391193097812136, fps: 23.73929370291974
加入15%疑难近似字符后日志如下
[2025/01/10 07:08:17] ppocr INFO: epoch: [1/50], global_step: 800, lr: 0.000001, CTCLoss: 27.405363, NRTRLoss: 3.751744, loss: 31.468330, avg_reader_cost: 0.00612 s, avg_batch_cost: 0.18858 s, avg_samples: 2.42, ips: 12.83303 samples/s, eta: 24 days, 15:34:07, max_mem_reserved: 2086 MB, max_mem_allocated: 1817 MB
[2025/01/10 07:08:35] ppocr INFO: epoch: [1/50], global_step: 900, lr: 0.000001, CTCLoss: 34.598011, NRTRLoss: 4.159418, loss: 39.047333, avg_reader_cost: 0.00216 s, avg_batch_cost: 0.17124 s, avg_samples: 2.32, ips: 13.54832 samples/s, eta: 24 days, 10:37:32, max_mem_reserved: 2086 MB, max_mem_allocated: 1821 MB
[2025/01/10 07:08:54] ppocr INFO: epoch: [1/50], global_step: 1000, lr: 0.000001, CTCLoss: 25.757986, NRTRLoss: 3.991220, loss: 29.173361, avg_reader_cost: 0.00482 s, avg_batch_cost: 0.18058 s, avg_samples: 2.27, ips: 12.57071 samples/s, eta: 24 days, 9:39:15, max_mem_reserved: 2086 MB, max_mem_allocated: 1821 MB
[2025/01/10 07:10:51] ppocr INFO: cur metric, acc: 0.3422069543056807, norm_edit_dis: 0.6666195348935893, fps: 23.206885368755316
Beta Was this translation helpful? Give feedback.
All reactions