ocr-projects-archive / ocr-tech-mps-integration /src /ocrtech /_vendor /paddleocr2pytorch /NOTICE.md
Add 1000 files (ocr-tech/tests/test_audit_limbu_book_missed_line_review_coverage.py ...)
d82db76 verified |
Download ocr-tech-mps-integration/src/ocrtech/_vendor/paddleocr2pytorch/NOTICE.md from prosperious/ocr-projects-archive: direct link, hf CLI and curl.
- Browser
- Download file 771 Bytes
-
https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/ocr-tech-mps-integration/src/ocrtech/_vendor/paddleocr2pytorch/NOTICE.md
- Command line
-
hf download hf://prosperious/ocr-projects-archive/ocr-tech-mps-integration/src/ocrtech/_vendor/paddleocr2pytorch/NOTICE.md
-
curl -L -o NOTICE.md https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/ocr-tech-mps-integration/src/ocrtech/_vendor/paddleocr2pytorch/NOTICE.md
771 Bytes
PaddleOCR2Pytorch vendored subset
Source: https://github.com/frotms/PaddleOCR2Pytorch
Revision: c05307fbd61e575d55f0fef0334026c7536aec76
License: Apache License 2.0. A copy is included as LICENSE.
Vendored files:
modeling/common.pymodeling/backbones/rec_lcnetv3.pymodeling/backbones/rec_svtrnet.pymodeling/necks/rnn.pymodeling/heads/rec_ctc_head.py
Local changes are deliberately limited to package-relative imports, MPS-safe
tensor placement/contiguity, correct guide detachment, and retaining dynamic
recognition width during training. The original fixed-width training pool in PPLCNetV3 was replaced with
height-only adaptive pooling so input width remains dynamic and the CTC path
produces one time step per four input pixels.