File size: 3,654 Bytes
495fe55 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
#
# For licensing see accompanying LICENSE file.
# Copyright (C) 2024 Apple Inc. All Rights Reserved.
#
from typing import List, Optional
import torch
import torch.nn as nn
from torch import Tensor
from mobileclip import logger
class GlobalPool(nn.Module):
"""
This layers applies global pooling over a 4D or 5D input tensor
Args:
pool_type (Optional[str]): Pooling type. It can be mean, rms, or abs. Default: `mean`
keep_dim (Optional[bool]): Do not squeeze the dimensions of a tensor. Default: `False`
Shape:
- Input: :math:`(N, C, H, W)` or :math:`(N, C, D, H, W)`
- Output: :math:`(N, C, 1, 1)` or :math:`(N, C, 1, 1, 1)` if keep_dim else :math:`(N, C)`
"""
pool_types = ["mean", "rms", "abs"]
def __init__(
self,
pool_type: Optional[str] = "mean",
keep_dim: Optional[bool] = False,
*args,
**kwargs
) -> None:
super().__init__()
if pool_type not in self.pool_types:
logger.error(
"Supported pool types are: {}. Got {}".format(
self.pool_types, pool_type
)
)
self.pool_type = pool_type
self.keep_dim = keep_dim
def _global_pool(self, x: Tensor, dims: List):
if self.pool_type == "rms": # root mean square
x = x**2
x = torch.mean(x, dim=dims, keepdim=self.keep_dim)
x = x**-0.5
elif self.pool_type == "abs": # absolute
x = torch.mean(torch.abs(x), dim=dims, keepdim=self.keep_dim)
else:
# default is mean
# same as AdaptiveAvgPool
x = torch.mean(x, dim=dims, keepdim=self.keep_dim)
return x
def forward(self, x: Tensor) -> Tensor:
if x.dim() == 4:
dims = [-2, -1]
elif x.dim() == 5:
dims = [-3, -2, -1]
else:
raise NotImplementedError("Currently 2D and 3D global pooling supported")
return self._global_pool(x, dims=dims)
class GlobalPool2D(nn.Module):
"""This class implements global pooling with linear projection."""
def __init__(self, in_dim: int, out_dim: int, *args, **kwargs) -> None:
super().__init__()
scale = in_dim**-0.5
self.pool = GlobalPool(pool_type="mean", keep_dim=False)
self.proj = nn.Parameter(scale * torch.randn(size=(in_dim, out_dim)))
self.in_dim = in_dim
self.out_dim = out_dim
def forward(self, x: Tensor, *args, **kwargs) -> Tensor:
# x is of shape [batch, in_dim]
assert (
x.dim() == 4
), "Input should be 4-dimensional (Batch x in_dim x in_height x in_width). Got: {}".format(
x.shape
)
# [batch, in_dim, in_height, in_width] --> [batch, in_dim]
x = self.pool(x)
# [batch, in_dim] x [in_dim, out_dim] --> [batch, out_dim]
x = x @ self.proj
return x
class SimpleImageProjectionHead(nn.Module):
"""This class implements linear projection head."""
def __init__(self, in_dim: int, out_dim: int) -> None:
super().__init__()
scale = in_dim**-0.5
self.proj = nn.Parameter(scale * torch.randn(size=(in_dim, out_dim)))
self.in_dim = in_dim
self.out_dim = out_dim
def forward(self, x: Tensor, *args, **kwargs) -> Tensor:
# x is of shape [batch, in_dim]
assert (
x.dim() == 2
), "Input should be 2-dimensional (Batch x in_dim). Got: {}".format(x.shape)
# [batch, in_dim] x [in_dim, out_dim] --> [batch, out_dim]
x = x @ self.proj
return x
|