MCPcopy Create free account
hub / github.com/FoundationVision/LlamaGen / drop_path

Function drop_path

utils/drop_path.py:4–21  ·  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... Se

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

Source from the content-addressed store, hash-verified

2import torch
3
4def drop_path(x, drop_prob: float = 0., training: bool = False, scale_by_keep: bool = True):
5 """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
6
7 This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
8 the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
9 See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
10 changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
11 'survival rate' as the argument.
12
13 """
14 if drop_prob == 0. or not training:
15 return x
16 keep_prob = 1 - drop_prob
17 shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
18 random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
19 if keep_prob > 0.0 and scale_by_keep:
20 random_tensor.div_(keep_prob)
21 return x * random_tensor
22
23
24class DropPath(torch.nn.Module):

Callers 1

forwardMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected