text_objseg
text_objseg copied to clipboard
Code release for Hu et al. Segmentation from Natural Language Expressions. in ECCV, 2016
the link of refit dataset is invaliable, could you please release a validate link,thank you
https://github.com/ronghanghu/text_objseg/blob/be664d66c72319363691628958727124ea38cad8/models/processing_tools.py#L6 Hi, may I ask why spatial channel number is eight rather than two, which mismatches the claim in the paper: _...we obtain a w×h×(D_im +2) representation containing local image...
Hi ronghang, I am reading your excellent work "Segmentation from Natural Language Expressions" , I am wondering someting about the Dtext = 1000 dimensional hidden state h, which is obtained...
Hey ronghang This is ravi , i am really amazed by the work you are doing, specially this segmentation model using NLP, i had some query regarding it. I am...
Hi, I'm getting a different prediction that one shown on the page. I am running the demo script as is on TF v0.7.0. 
Hi ronghang I am trying to train the high resolution model using your code. I followed all the instructions in the README, and did not change any parameters in the...