import torch
from torch import nn
[docs]class DropPath(nn.Module):
"""
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
Code taken from TIMM (https://github.com/rwightman/pytorch-image-models)
Apache License 2.0
"""
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
[docs] def forward(self, x):
if self.drop_prob == 0. or not self.training:
return x
keep_prob = 1 - self.drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output