train the model about icnet-tensorflow HOT 10 CLOSED

Hey guys, I have updated the repo.

from icnet-tensorflow.

Hey, @UndeadBlow , I have already done, now I am checking the performance.

from icnet-tensorflow.

Hey @HoracceFeng , I will provide the training code in recent days. What kinds of dataset do you want to use? Maybe I can give you some suggestions.

from icnet-tensorflow.

waiting for the train code

from icnet-tensorflow.

Hi, the datasets are some gray level images, and just have two classes.

from icnet-tensorflow.

waiting for the train code +1
And I just want to do perdestrian segmentation.
Because after I compared the provided checkpoint icnet model with fcn-8s in terms of perdestrian segmentation accuracy, it seems that the icnet model here do not show advantage and perform even worse than fcn_8s.
So, maybe i should train a specialized icnet model for perdestrian segmentation?

from icnet-tensorflow.

Hey, @ifangcheng , I think ICNet model focus on "real-time" segmentation, so it will get faster inference time at a sacrifice of accuracy. So, if you just want to do pedestrian segmentation, you can take PSPNet into your consideration, much slower but accurate. I have already implemented it too, you can take a look on it.

from icnet-tensorflow.

@hellochick， thanks for the suggestion.
However, real-time is also very important for me.
I suppose ICnet when trained specially for perdestrian segmentation may improve the accuracy than the provided model which is not focusing on perdestrian segmentation, am I right?
does that make sense?

from icnet-tensorflow.

Hi, @hellochick, any updates about train?

from icnet-tensorflow.

from icnet-tensorflow.