mirror of https://github.com/hero-y/BHRL
197 lines
7.4 KiB
Python
197 lines
7.4 KiB
Python
|
import warnings
|
||
|
|
|
||
|
|
import torch.nn as nn
|
||
|
|
from mmcv.cnn import ConvModule
|
||
|
|
from mmcv.runner import BaseModule
|
||
|
|
from torch.nn.modules.batchnorm import _BatchNorm
|
||
|
|
|
||
|
|
from ..builder import BACKBONES
|
||
|
|
from ..utils import InvertedResidual, make_divisible
|
||
|
|
|
||
|
|
|
||
|
|
@BACKBONES.register_module()
|
||
|
|
class MobileNetV2(BaseModule):
|
||
|
|
"""MobileNetV2 backbone.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
widen_factor (float): Width multiplier, multiply number of
|
||
|
|
channels in each layer by this amount. Default: 1.0.
|
||
|
|
out_indices (Sequence[int], optional): Output from which stages.
|
||
|
|
Default: (1, 2, 4, 7).
|
||
|
|
frozen_stages (int): Stages to be frozen (all param fixed).
|
||
|
|
Default: -1, which means not freezing any parameters.
|
||
|
|
conv_cfg (dict, optional): 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.
|
||
|
|
pretrained (str, optional): model pretrained path. Default: None
|
||
|
|
init_cfg (dict or list[dict], optional): Initialization config dict.
|
||
|
|
Default: None
|
||
|
|
"""
|
||
|
|
|
||
|
|
# 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=(1, 2, 4, 7),
|
||
|
|
frozen_stages=-1,
|
||
|
|
conv_cfg=None,
|
||
|
|
norm_cfg=dict(type='BN'),
|
||
|
|
act_cfg=dict(type='ReLU6'),
|
||
|
|
norm_eval=False,
|
||
|
|
with_cp=False,
|
||
|
|
pretrained=None,
|
||
|
|
init_cfg=None):
|
||
|
|
super(MobileNetV2, self).__init__(init_cfg)
|
||
|
|
|
||
|
|
self.pretrained = pretrained
|
||
|
|
assert not (init_cfg and pretrained), \
|
||
|
|
'init_cfg and pretrained cannot be setting at the same time'
|
||
|
|
if isinstance(pretrained, str):
|
||
|
|
warnings.warn('DeprecationWarning: pretrained is a deprecated, '
|
||
|
|
'please use "init_cfg" instead')
|
||
|
|
self.init_cfg = dict(type='Pretrained', checkpoint=pretrained)
|
||
|
|
elif pretrained is None:
|
||
|
|
if init_cfg is None:
|
||
|
|
self.init_cfg = [
|
||
|
|
dict(type='Kaiming', layer='Conv2d'),
|
||
|
|
dict(
|
||
|
|
type='Constant',
|
||
|
|
val=1,
|
||
|
|
layer=['_BatchNorm', 'GroupNorm'])
|
||
|
|
]
|
||
|
|
else:
|
||
|
|
raise TypeError('pretrained must be a str or None')
|
||
|
|
|
||
|
|
self.widen_factor = widen_factor
|
||
|
|
self.out_indices = out_indices
|
||
|
|
if not set(out_indices).issubset(set(range(0, 8))):
|
||
|
|
raise ValueError('out_indices must be a subset of range'
|
||
|
|
f'(0, 8). But received {out_indices}')
|
||
|
|
|
||
|
|
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')
|
||
|
|
|
||
|
|
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,
|
||
|
|
mid_channels=int(round(self.in_channels * expand_ratio)),
|
||
|
|
stride=stride,
|
||
|
|
with_expand_conv=expand_ratio != 1,
|
||
|
|
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)
|
||
|
|
|
||
|
|
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
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
"""Forward function."""
|
||
|
|
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)
|
||
|
|
return tuple(outs)
|
||
|
|
|
||
|
|
def train(self, mode=True):
|
||
|
|
"""Convert the model into training mode while keep normalization layer
|
||
|
|
frozen."""
|
||
|
|
super(MobileNetV2, self).train(mode)
|
||
|
|
self._freeze_stages()
|
||
|
|
if mode and self.norm_eval:
|
||
|
|
for m in self.modules():
|
||
|
|
# trick: eval have effect on BatchNorm only
|
||
|
|
if isinstance(m, _BatchNorm):
|
||
|
|
m.eval()
|