# Copyright (c) Alibaba, Inc. and its affiliates.
import math
import torch.nn as nn
from ..modelzoo import resnext as model_urls
from ..registry import BACKBONES
from ..utils import build_conv_layer, build_norm_layer
from .resnet import Bottleneck as _Bottleneck
from .resnet import ResNet
[docs]class Bottleneck(_Bottleneck):
[docs] def __init__(self, inplanes, planes, groups=1, base_width=4, **kwargs):
"""Bottleneck block for ResNeXt.
If style is "pytorch", the stride-two layer is the 3x3 conv layer,
if it is "caffe", the stride-two layer is the first 1x1 conv layer.
"""
super(Bottleneck, self).__init__(inplanes, planes, **kwargs)
if groups == 1:
width = self.planes
else:
width = math.floor(self.planes * (base_width / 64)) * groups
self.norm1_name, norm1 = build_norm_layer(
self.norm_cfg, width, postfix=1)
self.norm2_name, norm2 = build_norm_layer(
self.norm_cfg, width, postfix=2)
self.norm3_name, norm3 = build_norm_layer(
self.norm_cfg, self.planes * self.expansion, postfix=3)
self.conv1 = build_conv_layer(
self.conv_cfg,
self.inplanes,
width,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
fallback_on_stride = False
self.conv2 = build_conv_layer(
self.conv_cfg,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=self.dilation,
dilation=self.dilation,
groups=groups,
bias=False)
self.add_module(self.norm2_name, norm2)
self.conv3 = build_conv_layer(
self.conv_cfg,
width,
self.planes * self.expansion,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
[docs]def make_res_layer(block,
inplanes,
planes,
blocks,
stride=1,
dilation=1,
groups=1,
base_width=4,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN')):
downsample = None
if stride != 1 or inplanes != planes * block.expansion:
downsample = nn.Sequential(
build_conv_layer(
conv_cfg,
inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
build_norm_layer(norm_cfg, planes * block.expansion)[1],
)
layers = []
layers.append(
block(
inplanes=inplanes,
planes=planes,
stride=stride,
dilation=dilation,
downsample=downsample,
groups=groups,
base_width=base_width,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg))
inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(
block(
inplanes=inplanes,
planes=planes,
stride=1,
dilation=dilation,
groups=groups,
base_width=base_width,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg))
return nn.Sequential(*layers)
[docs]@BACKBONES.register_module
class ResNeXt(ResNet):
"""ResNeXt backbone.
Args:
depth (int): Depth of resnet, from {18, 34, 50, 101, 152}.
in_channels (int): Number of input image channels. Normally 3.
num_stages (int): Resnet stages, normally 4.
groups (int): Group of resnext.
base_width (int): Base width of resnext.
strides (Sequence[int]): Strides of the first block of each stage.
dilations (Sequence[int]): Dilation of each stage.
out_indices (Sequence[int]): Output from which stages.
style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
layer is the 3x3 conv layer, otherwise the stride-two layer is
the first 1x1 conv layer.
frozen_stages (int): Stages to be frozen (all param fixed). -1 means
not freezing any parameters.
norm_cfg (dict): dictionary to construct and config norm layer.
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.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
zero_init_residual (bool): whether to use zero init for last norm layer
in resblocks to let them behave as identity.
Example:
>>> from easycv.models import ResNeXt
>>> import torch
>>> self = ResNeXt(depth=50)
>>> self.eval()
>>> inputs = torch.rand(1, 3, 32, 32)
>>> level_outputs = self.forward(inputs)
>>> for level_out in level_outputs:
... print(tuple(level_out.shape))
(1, 256, 8, 8)
(1, 512, 4, 4)
(1, 1024, 2, 2)
(1, 2048, 1, 1)
"""
arch_settings = {
50: (Bottleneck, (3, 4, 6, 3)),
101: (Bottleneck, (3, 4, 23, 3)),
152: (Bottleneck, (3, 8, 36, 3))
}
[docs] def __init__(self, groups=1, base_width=4, **kwargs):
super(ResNeXt, self).__init__(**kwargs)
self.groups = groups
self.base_width = base_width
self.inplanes = 64
self.res_layers = []
for i, num_blocks in enumerate(self.stage_blocks):
stride = self.strides[i]
dilation = self.dilations[i]
planes = 64 * 2**i
res_layer = make_res_layer(
self.block,
self.inplanes,
planes,
num_blocks,
stride=stride,
dilation=dilation,
groups=self.groups,
base_width=self.base_width,
style=self.style,
with_cp=self.with_cp,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
)
self.inplanes = planes * self.block.expansion
layer_name = 'layer{}'.format(i + 1)
self.add_module(layer_name, res_layer)
self.res_layers.append(layer_name)
self._freeze_stages()
self.default_pretrained_model_path = model_urls.get(
self.__class__.__name__ + str(self.depth) + '-' +
str(self.groups) + 'x' + str(self.base_width) + 'd', None)