Open KTXKIKI opened 7 months ago
Hello, looks interesting. Does it work on CPU as well? What is FPS performance? Generally, it would be great to add a good model for OCR, but actually there are not resources to do it now.
你好,看起来很有趣。它也适用于 CPU 吗?什么是 FPS 性能?一般来说,为 OCR 添加一个好的模型会很棒,但实际上现在没有资源来做。
of course olso support CPU and GPU
你好,看起来很有趣。它也适用于 CPU 吗?什么是 FPS 性能?一般来说,为 OCR 添加一个好的模型会很棒,但实际上现在没有资源来做。
cpu inference for hundreds of milliseconds gpu inference Decades of milliseconds
Paddleocr is a universal ocr model that supports both Chinese and English as well as various special symbols I found some dockers to create image files for it: https://github.com/PaddlePaddle/PaddleOCR/tree/main/deploy/docker I think the development of the main.py file should become easier
I think we can learn from it:https://github.com/cvat-ai/cvat/tree/develop/serverless/openvino/omz/intel/face-detection-0205/nuclio
Actions before raising this issue
Is your feature request related to a problem? Please describe.
https://github.com/PaddlePaddle/PaddleOCR paddlepaddle-GPU环境组件.zip PaddleOCR.zip This is done by running script comments locally and uploading them, which may be integrated CVAT
Describe the solution you'd like
No response
Describe alternatives you've considered
No response
Additional context
No response