MCPcopy Index your code
hub / github.com/ActiveVisionLab/DFNet / rgb_loss

Function rgb_loss

script/feature/direct_feature_matching.py:95–100  ·  view source on GitHub ↗

Compute RGB MSE Loss, original from NeRF Paper

(rgb, target, extras)

Source from the content-addressed store, hash-verified

93 return features, pose
94
95def rgb_loss(rgb, target, extras):
96 ''' Compute RGB MSE Loss, original from NeRF Paper '''
97 # Compute MSE loss between predicted and true RGB.
98 img_loss = img2mse(rgb, target)
99 loss = img_loss
100 return loss
101
102def normalize_features(tensor, value_range=None, scale_each: bool = False):
103 ''' Find unit norm of channel wise feature

Callers 2

train_on_feature_batchFunction · 0.70
train_on_batchFunction · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected