1 Star 0 Fork 0

TeoNiX/PaddleOCR

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
PPOCRLabel
StyleText
configs
deploy
doc
datasets
demo
doc_ch
doc_en
FAQ_en.md
add_new_algorithm_en.md
algorithm_overview_en.md
android_demo_en.md
angle_class_en.md
benchmark_en.md
config_en.md
customize_en.md
data_annotation_en.md
data_synthesis_en.md
datasets_en.md
detection_en.md
distributed_training.md
environment_en.md
handwritten_datasets_en.md
inference_en.md
inference_ppocr_en.md
installation_en.md
models_en.md
models_list_en.md
multi_languages_en.md
paddleOCR_overview_en.md
pgnet_en.md
quickstart_en.md
recognition_en.md
reference_en.md
training_en.md
tree_en.md
tricks_en.md
update_en.md
vertical_and_multilingual_datasets_en.md
visualization_en.md
whl_en.md
fonts
imgs
imgs_en
imgs_results
imgs_words
imgs_words_en
install
table
tricks
PPOCR.pdf
PaddleOCR_log.png
joinus.PNG
ocr-android-easyedge.png
overview.png
overview_en.png
pgnet_framework.png
ppocr_framework.png
ppocrv2_framework.jpg
ppocr
ppstructure
tools
.clang_format.hook
.gitignore
.pre-commit-config.yaml
.style.yapf
LICENSE
MANIFEST.in
README.md
README_ch.md
__init__.py
paddleocr.py
requirements.txt
setup.py
train.sh
克隆/下载
benchmark_en.md 1.90 KB
一键复制 编辑 原始数据 按行查看 历史
xiaoting 提交于 4年前 . Update benchmark_en.md

Benchmark

This document gives the performance of the series models for Chinese and English recognition.

Test Data

We collected 300 images for different real application scenarios to evaluate the overall OCR system, including contract samples, license plates, nameplates, train tickets, test sheets, forms, certificates, street view images, business cards, digital meter, etc. The following figure shows some images of the test set.

Measurement

Explanation:

  • The long size of the input for the text detector is 960.

  • The evaluation time-consuming stage is the complete stage from image input to result output, including image pre-processing and post-processing.

  • Intel Xeon 6148 is the server-side CPU model. Intel MKL-DNN is used in the test to accelerate the CPU prediction speed.

  • Snapdragon 855 is a mobile processing platform model.

Compares the model size and F-score:

Model Name Model Size
of the
Whole System(M)
Model Size
of the Text
Detector(M)
Model Size
of the Direction
Classifier(M)
Model Size
of the Text
Recognizer (M)
F-score
PP-OCRv2 11.6 3.0 0.9 8.6 0.5224
PP-OCR mobile 8.1 2.6 0.9 4.6 0.503
PP-OCR server 155.1 47.2 0.9 107 0.570

Compares the time-consuming on CPU and T4 GPU (ms):

Model Name CPU T4 GPU
PP-OCRv2 330 111
PP-OCR mobile 356 116
PP-OCR server 1056 200

More indicators of PP-OCR series models can be referred to PP-OCR Benchmark

Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/teonix/PaddleOCR.git
git@gitee.com:teonix/PaddleOCR.git
teonix
PaddleOCR
PaddleOCR
release/2.3

搜索帮助