You are reading the documentation for MMClassification 0.x, which will soon be deprecated at the end of 2022. We recommend you upgrade to MMClassification 1.0 to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check the installation tutorial, migration tutorial and changelog for more details.

Source code for

# Copyright (c) OpenMMLab. All rights reserved.
import torch
import torch.nn as nn

from ..builder import NECKS

[docs]@NECKS.register_module() class GlobalAveragePooling(nn.Module): """Global Average Pooling neck. Note that we use `view` to remove extra channel after pooling. We do not use `squeeze` as it will also remove the batch dimension when the tensor has a batch dimension of size 1, which can lead to unexpected errors. Args: dim (int): Dimensions of each sample channel, can be one of {1, 2, 3}. Default: 2 """ def __init__(self, dim=2): super(GlobalAveragePooling, self).__init__() assert dim in [1, 2, 3], 'GlobalAveragePooling dim only support ' \ f'{1, 2, 3}, get {dim} instead.' if dim == 1: = nn.AdaptiveAvgPool1d(1) elif dim == 2: = nn.AdaptiveAvgPool2d((1, 1)) else: = nn.AdaptiveAvgPool3d((1, 1, 1)) def init_weights(self): pass
[docs] def forward(self, inputs): if isinstance(inputs, tuple): outs = tuple([ for x in inputs]) outs = tuple( [out.view(x.size(0), -1) for out, x in zip(outs, inputs)]) elif isinstance(inputs, torch.Tensor): outs = outs = outs.view(inputs.size(0), -1) else: raise TypeError('neck inputs should be tuple or torch.tensor') return outs
Read the Docs v: latest
On Read the Docs
Project Home

Free document hosting provided by Read the Docs.