MCPcopy Create free account
hub / github.com/PowerHouseMan/ComfyUI-AdvancedLivePortrait / drop_path

Function drop_path

LivePortrait/modules/util.py:407–424  ·  view source on GitHub ↗

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for EfficientNet, etc networks, however, the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper... S

(x, drop_prob=0., training=False, scale_by_keep=True)

Source from the content-addressed store, hash-verified

405
406
407def drop_path(x, drop_prob=0., training=False, scale_by_keep=True):
408 """ Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
409
410 This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
411 the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
412 See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
413 changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
414 'survival rate' as the argument.
415
416 """
417 if drop_prob == 0. or not training:
418 return x
419 keep_prob = 1 - drop_prob
420 shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
421 random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
422 if keep_prob > 0.0 and scale_by_keep:
423 random_tensor.div_(keep_prob)
424 return x * random_tensor
425
426
427class DropPath(nn.Module):

Callers 1

forwardMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected