Shortcuts

Source code for mmpose.models.backbones.mobilenet_v2

# Copyright (c) OpenMMLab. All rights reserved.
import copy
import logging

import torch.nn as nn
import torch.utils.checkpoint as cp
from mmcv.cnn import ConvModule, constant_init, kaiming_init
from torch.nn.modules.batchnorm import _BatchNorm

from ..builder import BACKBONES
from .base_backbone import BaseBackbone
from .utils import load_checkpoint, make_divisible


class InvertedResidual(nn.Module):
    """InvertedResidual block for MobileNetV2.

    Args:
        in_channels (int): The input channels of the InvertedResidual block.
        out_channels (int): The output channels of the InvertedResidual block.
        stride (int): Stride of the middle (first) 3x3 convolution.
        expand_ratio (int): adjusts number of channels of the hidden layer
            in InvertedResidual by this amount.
        conv_cfg (dict): Config dict for convolution layer.
            Default: None, which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN').
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='ReLU6').
        with_cp (bool): Use checkpoint or not. Using checkpoint will save some
            memory while slowing down the training speed. Default: False.
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 stride,
                 expand_ratio,
                 conv_cfg=None,
                 norm_cfg=dict(type='BN'),
                 act_cfg=dict(type='ReLU6'),
                 with_cp=False):
        # Protect mutable default arguments
        norm_cfg = copy.deepcopy(norm_cfg)
        act_cfg = copy.deepcopy(act_cfg)
        super().__init__()
        self.stride = stride
        assert stride in [1, 2], f'stride must in [1, 2]. ' \
            f'But received {stride}.'
        self.with_cp = with_cp
        self.use_res_connect = self.stride == 1 and in_channels == out_channels
        hidden_dim = int(round(in_channels * expand_ratio))

        layers = []
        if expand_ratio != 1:
            layers.append(
                ConvModule(
                    in_channels=in_channels,
                    out_channels=hidden_dim,
                    kernel_size=1,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))
        layers.extend([
            ConvModule(
                in_channels=hidden_dim,
                out_channels=hidden_dim,
                kernel_size=3,
                stride=stride,
                padding=1,
                groups=hidden_dim,
                conv_cfg=conv_cfg,
                norm_cfg=norm_cfg,
                act_cfg=act_cfg),
            ConvModule(
                in_channels=hidden_dim,
                out_channels=out_channels,
                kernel_size=1,
                conv_cfg=conv_cfg,
                norm_cfg=norm_cfg,
                act_cfg=None)
        ])
        self.conv = nn.Sequential(*layers)

    def forward(self, x):

        def _inner_forward(x):
            if self.use_res_connect:
                return x + self.conv(x)
            return self.conv(x)

        if self.with_cp and x.requires_grad:
            out = cp.checkpoint(_inner_forward, x)
        else:
            out = _inner_forward(x)

        return out


[docs]@BACKBONES.register_module() class MobileNetV2(BaseBackbone): """MobileNetV2 backbone. Args: widen_factor (float): Width multiplier, multiply number of channels in each layer by this amount. Default: 1.0. out_indices (None or Sequence[int]): Output from which stages. Default: (7, ). frozen_stages (int): Stages to be frozen (all param fixed). Default: -1, which means not freezing any parameters. conv_cfg (dict): Config dict for convolution layer. Default: None, which means using conv2d. norm_cfg (dict): Config dict for normalization layer. Default: dict(type='BN'). act_cfg (dict): Config dict for activation layer. Default: dict(type='ReLU6'). norm_eval (bool): Whether to set norm layers to eval mode, namely, freeze running stats (mean and var). Note: Effect on Batch Norm and its variants only. Default: False. with_cp (bool): Use checkpoint or not. Using checkpoint will save some memory while slowing down the training speed. Default: False. """ # Parameters to build layers. 4 parameters are needed to construct a # layer, from left to right: expand_ratio, channel, num_blocks, stride. arch_settings = [[1, 16, 1, 1], [6, 24, 2, 2], [6, 32, 3, 2], [6, 64, 4, 2], [6, 96, 3, 1], [6, 160, 3, 2], [6, 320, 1, 1]] def __init__(self, widen_factor=1., out_indices=(7, ), frozen_stages=-1, conv_cfg=None, norm_cfg=dict(type='BN'), act_cfg=dict(type='ReLU6'), norm_eval=False, with_cp=False): # Protect mutable default arguments norm_cfg = copy.deepcopy(norm_cfg) act_cfg = copy.deepcopy(act_cfg) super().__init__() self.widen_factor = widen_factor self.out_indices = out_indices for index in out_indices: if index not in range(0, 8): raise ValueError('the item in out_indices must in ' f'range(0, 8). But received {index}') if frozen_stages not in range(-1, 8): raise ValueError('frozen_stages must be in range(-1, 8). ' f'But received {frozen_stages}') self.out_indices = out_indices self.frozen_stages = frozen_stages self.conv_cfg = conv_cfg self.norm_cfg = norm_cfg self.act_cfg = act_cfg self.norm_eval = norm_eval self.with_cp = with_cp self.in_channels = make_divisible(32 * widen_factor, 8) self.conv1 = ConvModule( in_channels=3, out_channels=self.in_channels, kernel_size=3, stride=2, padding=1, conv_cfg=self.conv_cfg, norm_cfg=self.norm_cfg, act_cfg=self.act_cfg) self.layers = [] for i, layer_cfg in enumerate(self.arch_settings): expand_ratio, channel, num_blocks, stride = layer_cfg out_channels = make_divisible(channel * widen_factor, 8) inverted_res_layer = self.make_layer( out_channels=out_channels, num_blocks=num_blocks, stride=stride, expand_ratio=expand_ratio) layer_name = f'layer{i + 1}' self.add_module(layer_name, inverted_res_layer) self.layers.append(layer_name) if widen_factor > 1.0: self.out_channel = int(1280 * widen_factor) else: self.out_channel = 1280 layer = ConvModule( in_channels=self.in_channels, out_channels=self.out_channel, kernel_size=1, stride=1, padding=0, conv_cfg=self.conv_cfg, norm_cfg=self.norm_cfg, act_cfg=self.act_cfg) self.add_module('conv2', layer) self.layers.append('conv2')
[docs] def make_layer(self, out_channels, num_blocks, stride, expand_ratio): """Stack InvertedResidual blocks to build a layer for MobileNetV2. Args: out_channels (int): out_channels of block. num_blocks (int): number of blocks. stride (int): stride of the first block. Default: 1 expand_ratio (int): Expand the number of channels of the hidden layer in InvertedResidual by this ratio. Default: 6. """ layers = [] for i in range(num_blocks): if i >= 1: stride = 1 layers.append( InvertedResidual( self.in_channels, out_channels, stride, expand_ratio=expand_ratio, conv_cfg=self.conv_cfg, norm_cfg=self.norm_cfg, act_cfg=self.act_cfg, with_cp=self.with_cp)) self.in_channels = out_channels return nn.Sequential(*layers)
[docs] def init_weights(self, pretrained=None): if isinstance(pretrained, str): logger = logging.getLogger() load_checkpoint(self, pretrained, strict=False, logger=logger) elif pretrained is None: for m in self.modules(): if isinstance(m, nn.Conv2d): kaiming_init(m) elif isinstance(m, (_BatchNorm, nn.GroupNorm)): constant_init(m, 1) else: raise TypeError('pretrained must be a str or None')
[docs] def forward(self, x): x = self.conv1(x) outs = [] for i, layer_name in enumerate(self.layers): layer = getattr(self, layer_name) x = layer(x) if i in self.out_indices: outs.append(x) if len(outs) == 1: return outs[0] return tuple(outs)
def _freeze_stages(self): if self.frozen_stages >= 0: for param in self.conv1.parameters(): param.requires_grad = False for i in range(1, self.frozen_stages + 1): layer = getattr(self, f'layer{i}') layer.eval() for param in layer.parameters(): param.requires_grad = False
[docs] def train(self, mode=True): super().train(mode) self._freeze_stages() if mode and self.norm_eval: for m in self.modules(): if isinstance(m, _BatchNorm): m.eval()
Read the Docs v: latest
Versions
latest
1.x
v0.14.0
fix-doc
cn_doc
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.