File size: 2,666 Bytes
d670799 |
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 |
# Copyright (c) OpenMMLab. All rights reserved.
import torch
import torch.nn as nn
from mmengine.model.weight_init import normal_init
from mmaction.registry import MODELS
from mmaction.utils import ConfigType
from .base import BaseHead
@MODELS.register_module()
class TSNAudioHead(BaseHead):
"""Classification head for TSN on audio.
Args:
num_classes (int): Number of classes to be classified.
in_channels (int): Number of channels in input feature.
loss_cls (Union[dict, ConfigDict]): Config for building loss.
Defaults to ``dict(type='CrossEntropyLoss')``.
spatial_type (str): Pooling type in spatial dimension.
Defaults to ``avg``.
dropout_ratio (float): Probability of dropout layer. Defaults to 0.4.
init_std (float): Std value for Initiation. Defaults to 0.01.
"""
def __init__(self,
num_classes: int,
in_channels: int,
loss_cls: ConfigType = dict(type='CrossEntropyLoss'),
spatial_type: str = 'avg',
dropout_ratio: float = 0.4,
init_std: float = 0.01,
**kwargs) -> None:
super().__init__(num_classes, in_channels, loss_cls=loss_cls, **kwargs)
self.spatial_type = spatial_type
self.dropout_ratio = dropout_ratio
self.init_std = init_std
if self.spatial_type == 'avg':
# use `nn.AdaptiveAvgPool2d` to adaptively match the in_channels.
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
else:
self.avg_pool = None
if self.dropout_ratio != 0:
self.dropout = nn.Dropout(p=self.dropout_ratio)
else:
self.dropout = None
self.fc_cls = nn.Linear(self.in_channels, self.num_classes)
def init_weights(self) -> None:
"""Initiate the parameters from scratch."""
normal_init(self.fc_cls, std=self.init_std)
def forward(self, x: torch.Tensor) -> torch.Tensor:
"""Defines the computation performed at every call.
Args:
x (torch.Tensor): The input data.
Returns:
torch.Tensor: The classification scores for input samples.
"""
# [N * num_segs, in_channels, h, w]
x = self.avg_pool(x)
# [N, in_channels, 1, 1]
x = x.view(x.size(0), -1)
# [N, in_channels]
if self.dropout is not None:
x = self.dropout(x)
# [N, in_channels]
cls_score = self.fc_cls(x)
# [N, num_classes]
return cls_score
|