MCPcopy Create free account
hub / github.com/DIVE128/DMVSNet / depth_regression

Function depth_regression

networks/module.py:454–460  ·  view source on GitHub ↗
(p, depth_values,axis=1)

Source from the content-addressed store, hash-verified

452
453
454def depth_regression(p, depth_values,axis=1):
455 if depth_values.dim() <= 2:
456 # print("regression dim <= 2")
457 depth_values = depth_values.view(*depth_values.shape, 1, 1)
458 depth = torch.sum(p * depth_values, axis=axis)
459
460 return depth
461
462
463def winner_take_all(prob_volume, depth_values):

Callers 2

forwardMethod · 0.85
refineMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected