test on a video file about mega.pytorch HOT 7 CLOSED

@SonrLax Because when MEGA makes a prediction, it doesn't rely only on just one image, so the demo is not directly applicable. I need to preprocess the whole video into a queue and sequentially process them. It's not hard but a bit tricky. :)

from mega.pytorch.

@Scalsol

Any help you can give?

Thanks

from mega.pytorch.

Sorry for late reply! You may refer to mmdetection to see how they inference on a piece of video and adjust some code of this repo accordingly to achieve the behavior you want. After the NIPS ddl I will try to add demo to enable inference on video files but currently I have no time :( Hope this piece of message would help!

from mega.pytorch.

I will take a look at mmdetection code and try to do it myself.
In the meantime, it will be great that you can add one after NIPS in case I am not able to do it

Thanks,

from mega.pytorch.

@Scalsol Since MEGA is based on maskrcnn_benchmark, why not refer to demo ? Just curious.
Thanks !

from mega.pytorch.

I've added demo for visualization, closing this. Feel free to reopen it if the visualization doesn't work :)

from mega.pytorch.

!hi, I get segmentation fault whenever i try to do demo on my video, or i get Imagelist not scriptable any help please ?

from mega.pytorch.