akansal1

facing memory leak issues of CPU, on GPU working fine

it is a **proposal**, and yes I want to do something like that.

In that case, you may have to look at using virtual columns, that allow you to treat inferred or derived value as a dimension.

Plywood uses chronoshift to this calculation https://github.com/implydata/chronoshift/blob/master/src/duration/duration.ts#L256 Which is using criteria defined in https://github.com/implydata/chronoshift/blob/master/src/floor-shift-ceil/floor-shift-ceil.ts So, in principle making changes in chronoshift logic should work and you will not require to...

@yunyaoXYY you use following to reproduce: > Inference via **PaddleOCR** ```python from paddleocr import PaddleOCR,draw_ocr import cv2 img_path = ocr = PaddleOCR(use_angle_cls=True, lang='en') ocr(cv2.imread(img_path)) ``` ``` [2022/12/02 01:56:54] ppocr DEBUG:...

@yunyaoXYY I tried the same on your sample image and got the following results: ```JSON { "FastDeploy": { "LRE": 0.3414466977119446, "tJYj 155": 0.5437671542167664, "1L4": 0.4430263042449951, "T252935": 0.9433053135871887 }, "PaddleOCR": {...

@robertervin were you able to solve this problem ?