while running demo on my own data
DODoubleJ opened this issue · 8 comments
When I replaced the demo images with my own data, an error occurred and it told me the shape of my images tensor is not the required shape:[1,224,224], so if I want to run demo on my own data, the only way I can choose is change the size of my data, because if I change the default tensor in the code, I will encounter more troubles, something like changing the pretrained model.
So if the code is only suitable for the images in the shape of 224*224? I'm confused.
Yes we resize all image to 224*224 as input
@arieling From your Youtube demo video, you are crop a patch from image and then predict polygons from it. Does the input is just the croped path or the whole image?
@jinfagang we shore images in our server. In our demo front-end gives bounding box to backend and our dataProvider crops the full image according to it.
Hi, how to crop the full image according to the bounding box ?And is this the latest model？
@yohacai That part of code is not released yet. Hopefully we will release training code & full model & data & demo this week.
@arieling Hoping for it
Thank you for the hard work! Am looking forward to it
Code released. Check https://github.com/fidler-lab/polyrnn-pp-pytorch and sign up to get our full code.