Megvii-BaseDetection/cvpods

How to do inference on a single image?[Usage]

VladuxRTK opened this issue · 1 comments

Please use this template to submit your problem or your question will NOT be properly tackled.


Describe what you want to do, including:

  1. what inputs you will provide, if any:
  2. what outputs you are expecting:

❓ What does an API do and how to use it?

I want to use an image from the susbset of test images from crowdhuman dataset.
I want to be able to run an inference on it and do the object detection on it, but there is no path assignment for pods_test...
Please tell me if there is a way for that

you can achieve this through modifying the dataset_dict in Dataset class, and only put your desired image into the dataset_dict. as a result, the length of the dataset will become 1.