I am currently training CONV-CRF, but I have not found the corresponding formula for these parameters in your paper? I don't know their specific meaning:
'pos_feats': {
'sdims': 3,
'compat': 3,
},
'col_feats': {
'sdims': 80,
'schan': 13, # schan depend on the input scale.
use schan = 13 for images in [0, 255]
# for normalized images in [-0.5, 0.5] try schan = 0.1
'compat': 10,
'use_bias': True
@HqWei Hello, as I got, you implemented train process, i also did it, but not correctly - the model doesn't learn anything. Could you share your implementation?
I am currently training CONV-CRF, but I have not found the corresponding formula for these parameters in your paper? I don't know their specific meaning: 'pos_feats': { 'sdims': 3, 'compat': 3, }, 'col_feats': { 'sdims': 80, 'schan': 13, # schan depend on the input scale.
use schan = 13 for images in [0, 255]