Open 9p15p opened 4 years ago
Hi, Thank you for your excellent work!
I want to know what the 'annotation_centroids.npy' and the centroids means. To be specific,I can't find something in paper related to
torch.argmin(torch.sqrt(torch.sum((img.unsqueeze(1) - centroids) ** 2, 2)), 1)
in function 'rgb2class'.Best wishes.
Here is my question in Chinese,which is consistent with the above:
'centroids'这个变量以及在dataset中的 'annotation_centroids.npy' 发挥了什么作用呢,我在论文中没有看到对应的信息。 关于'rgb2class'函数中的
torch.argmin(torch.sqrt(torch.sum((img.unsqueeze(1) - centroids) ** 2, 2)), 1)
具体含义麻烦您能解释一下吗祝好。
annotation is represented by rgb, in order to convert to label, we need a mapping tuple (r, g, b) -> interger (instance id), due to resize, annotation rgb value not exactly in the mapping's domain of definition, so take the nearest, this is why called centroids
and i have another question, why do you use 191 instead of 192? Thank you!
and i have another question, why do you use 191 instead of 192? Thank you!
Thank you for your reply.^_^ and I don't know what your question about '191' or '192' means. Do I use it somewhere?
and i have another question, why do you use 191 instead of 192? Thank you!
Thank you for your reply.^_^ and I don't know what your question about '191' or '192' means. Do I use it somewhere?
sorry, I mean in annotation_centroids.npy they use the value 191, but in palette it's 192
and i have another question, why do you use 191 instead of 192? Thank you!
Thank you for your reply.^_^ and I don't know what your question about '191' or '192' means. Do I use it somewhere?
sorry, I mean in annotation_centroids.npy they use the value 191, but in palette it's 192
Oh, I find this problem, too. Thank you.
Hi, Thank you for your excellent work!
I want to know what the 'annotation_centroids.npy' and the centroids means. To be specific,I can't find something in paper related to
torch.argmin(torch.sqrt(torch.sum((img.unsqueeze(1) - centroids) ** 2, 2)), 1)
in function 'rgb2class'.Best wishes.
Here is my question in Chinese,which is consistent with the above:
'centroids'这个变量以及在dataset中的 'annotation_centroids.npy' 发挥了什么作用呢,我在论文中没有看到对应的信息。 关于'rgb2class'函数中的
torch.argmin(torch.sqrt(torch.sum((img.unsqueeze(1) - centroids) ** 2, 2)), 1)
具体含义麻烦您能解释一下吗祝好。