ContextPrior
ContextPrior copied to clipboard
ycszen
Implementation for "Context Prior for Scene Segmentation"
Thank you for your sharing. I am very interested in your work and would like to know how soon the complete code of this work will be released. Thank you...
could you please provide code of Visualization of the Prior Map predicted by CP-Net
Many thanks for this great work. After reading your paper. I have some confusion. 1. You mention in your paper, you train your model over ADE20k with 480x480 which used...
Does anyone run this code based on mmsegmentation? How about the performance?
In my dataset, all pixels in some images are belongs to same label. This situation makes denominator in specificity become zero. Should I add eps in denominator, or set specificity...
softmax function needs LongTensor for the GT, if you downsample GT with pool or Interpolation, how to get LongTensor, then how to guarantee the downsampled GT is mainingful, which means...
from ..builder import LOSSES from .utils import weight_reduce_loss
File "D:\New_Era_Project\Local_similarity_project\mmseg\models\decode_heads\cp_head.py", line 235, in losses prior_loss = self.loss_prior_decode( File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\New_Era_Project\Local_similarity_project\mmseg\models\losses\affinity_loss.py", line 126, in forward unary_term = self.cls_criterion( File "D:\New_Era_Project\Local_similarity_project\mmseg\models\losses\affinity_loss.py", line...
