How to predict on a single cv2.mat?

PaddlePaddle / PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Apache License 2.0

12.34k stars 2.84k forks source link

How to predict on a single cv2.mat? #9024

Open LLsmile opened 2 weeks ago

LLsmile commented 2 weeks ago

问题确认 Search before asking

[X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

I want to predict images in my projects and all images have been loaded into memory. So I need to inference images in memory instead of loading image in disk.

LLsmile commented 2 weeks ago

The tools/infer.py needs image location in disk. Is there any example to inference image in memory?

lyuwenyu commented 2 weeks ago

目前不支持