Giters

icoz69 / CaNet

The code for paper "CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to use the model after train?

sanersbug opened this issue · comments

commented

I find that the forward need 4 parameter ,' query_rgb','support_rgb','support_mask','history_mask',
what's mean of the 'support_rgb','support_mask'? how can i get it , if it is any image with label?

when i use the network to predict a image , how modify the code ?

Thanks a lot!

commented

Support set: is the training set with few labelled examples. So you want to provide support RGB image and support 0/1 segmentation mask for the new class outside the 15 classes it was meta-trained on. query is the image you want to segment with an object from the new class. history_mask u can initialize to zeros in the beginning.

commented

Thank you very much! @MSiam
And would you mind give some advice about the predict period , how to modify the code to complete the inference.