search

Media-Smart / vedadet

A single stage object detection toolbox based on PyTorch
Apache License 2.0
498 stars 128 forks source link

how to inference on webcam or video? #15

Closed hyperf0cus closed 3 years ago

hyperf0cus commented 3 years ago

In infer.py you did it by data_pipeline. How to handle it when source is Webcam or Video frames?

hxcai commented 3 years ago

@hyperf0cus You can remove the transform LoadImageFromFile, and construct a same dict after reading image.

hyperf0cus commented 3 years ago

@hyperf0cus You can remove the transform LoadImageFromFile, and construct a same dict after reading image.

Thank you!

gd1925 commented 2 years ago

Hi, I am trying to run the code for a mp4 video, but I cant seem to understand what you mean by "construct a same dict after reading image". Could you please help? Thank you very much.

lixinru77 commented 1 year ago

do you solve this problem? please help me to come true.thank you