We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
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
[2025-01-17 00:54:37,502] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,505] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,506] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,508] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,511] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,515] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') [2025-01-17 00:54:37,518] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n') 2025-01-17 00:54:39.078 | INFO | magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 3509, cid_chars_radio: 0.0 2025-01-17 00:54:39.082 | WARNING | magic_pdf.filter.pdf_classify_by_type:classify:334 - pdf is not classified by area and text_len, by_image_area: False, by_text: True, by_avg_words: True, by_img_num: True, by_text_layout: True, by_img_narrow_strips: True, by_invalid_chars: True 2025-01-17 00:54:54.595 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.52 2025-01-17 00:55:21.352 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 26.75 2025-01-17 00:55:21.352 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 0, page total time: 41.28----- 2025-01-17 00:55:37.557 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.74 2025-01-17 00:55:49.726 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 12.16 2025-01-17 00:55:49.726 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 1, page total time: 26.91----- 2025-01-17 00:56:05.174 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.19 2025-01-17 00:56:08.088 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 2.9 2025-01-17 00:56:08.088 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 2, page total time: 17.1----- 2025-01-17 00:56:22.839 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 13.72 2025-01-17 00:56:42.865 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 20.02 2025-01-17 00:56:42.865 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 3, page total time: 33.75----- 2025-01-17 00:56:57.983 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.15 2025-01-17 00:57:18.312 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 20.32 2025-01-17 00:57:18.313 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 4, page total time: 34.48----- 2025-01-17 00:57:34.336 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.86 2025-01-17 00:57:35.842 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 1.5 2025-01-17 00:57:35.842 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 5, page total time: 16.37----- 2025-01-17 00:57:51.104 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.14 2025-01-17 00:58:12.490 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 21.38 2025-01-17 00:58:12.490 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 6, page total time: 35.53----- 2025-01-17 00:58:12.816 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:234 - gc time: 0.33 2025-01-17 00:58:12.816 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:238 - doc analyze time: 213.73, speed: 0.04 pages/second
虽然是cpu运行,但是layout的速度似乎还是不太正常,另外error日志是否对推理速度有影响
Linux
3.10
1.0.x
cpu
The text was updated successfully, but these errors were encountered:
linux arm环境运行需要升级到1.0.1以获得最佳性能
Sorry, something went wrong.
好的谢谢
No branches or pull requests
Description of the bug | 错误描述
[2025-01-17 00:54:37,502] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,505] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,506] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,508] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,511] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,515] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
[2025-01-17 00:54:37,518] [ ERROR] infer.py:218 - fast-langdetect:Error during language detection: predict processes one line at a time (remove '\n')
2025-01-17 00:54:39.078 | INFO | magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 3509, cid_chars_radio: 0.0
2025-01-17 00:54:39.082 | WARNING | magic_pdf.filter.pdf_classify_by_type:classify:334 - pdf is not classified by area and text_len, by_image_area: False, by_text: True, by_avg_words: True, by_img_num: True, by_text_layout: True, by_img_narrow_strips: True, by_invalid_chars: True
2025-01-17 00:54:54.595 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.52
2025-01-17 00:55:21.352 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 26.75
2025-01-17 00:55:21.352 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 0, page total time: 41.28-----
2025-01-17 00:55:37.557 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.74
2025-01-17 00:55:49.726 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 12.16
2025-01-17 00:55:49.726 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 1, page total time: 26.91-----
2025-01-17 00:56:05.174 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.19
2025-01-17 00:56:08.088 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 2.9
2025-01-17 00:56:08.088 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 2, page total time: 17.1-----
2025-01-17 00:56:22.839 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 13.72
2025-01-17 00:56:42.865 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 20.02
2025-01-17 00:56:42.865 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 3, page total time: 33.75-----
2025-01-17 00:56:57.983 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.15
2025-01-17 00:57:18.312 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 20.32
2025-01-17 00:57:18.313 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 4, page total time: 34.48-----
2025-01-17 00:57:34.336 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.86
2025-01-17 00:57:35.842 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 1.5
2025-01-17 00:57:35.842 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 5, page total time: 16.37-----
2025-01-17 00:57:51.104 | INFO | magic_pdf.model.pdf_extract_kit:call:202 - layout detection time: 14.14
2025-01-17 00:58:12.490 | INFO | magic_pdf.model.pdf_extract_kit:call:249 - ocr time: 21.38
2025-01-17 00:58:12.490 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:223 - -----page_id : 6, page total time: 35.53-----
2025-01-17 00:58:12.816 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:234 - gc time: 0.33
2025-01-17 00:58:12.816 | INFO | magic_pdf.model.doc_analyze_by_custom_model:doc_analyze:238 - doc analyze time: 213.73, speed: 0.04 pages/second
How to reproduce the bug | 如何复现
虽然是cpu运行,但是layout的速度似乎还是不太正常,另外error日志是否对推理速度有影响
Operating system | 操作系统
Linux
Python version | Python 版本
3.10
Software version | 软件版本 (magic-pdf --version)
1.0.x
Device mode | 设备模式
cpu
The text was updated successfully, but these errors were encountered: