mirror of https://github.com/alibaba/EasyCV.git
419 lines
13 KiB
Python
419 lines
13 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
from typing import List
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from mmcv.cnn import constant_init, kaiming_init
|
|
from torch.nn.modules.batchnorm import _BatchNorm
|
|
|
|
from ..registry import BACKBONES
|
|
from ..utils import build_conv_layer, build_norm_layer
|
|
|
|
|
|
class BasicBlock(nn.Module):
|
|
expansion = 1
|
|
|
|
def __init__(self,
|
|
inplanes,
|
|
planes,
|
|
stride=1,
|
|
dilation=1,
|
|
downsample=None,
|
|
style='pytorch',
|
|
with_cp=False,
|
|
conv_cfg=None,
|
|
norm_cfg=dict(type='BN')):
|
|
super(BasicBlock, self).__init__()
|
|
|
|
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
|
|
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
|
|
|
|
self.conv1 = build_conv_layer(
|
|
conv_cfg,
|
|
inplanes,
|
|
planes,
|
|
3,
|
|
stride=stride,
|
|
padding=dilation,
|
|
dilation=dilation,
|
|
bias=False)
|
|
self.add_module(self.norm1_name, norm1)
|
|
self.conv2 = build_conv_layer(
|
|
conv_cfg, planes, planes, 3, padding=1, bias=False)
|
|
self.add_module(self.norm2_name, norm2)
|
|
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
self.dilation = dilation
|
|
assert not with_cp
|
|
|
|
@property
|
|
def norm1(self):
|
|
return getattr(self, self.norm1_name)
|
|
|
|
@property
|
|
def norm2(self):
|
|
return getattr(self, self.norm2_name)
|
|
|
|
def forward(self, x):
|
|
identity = x
|
|
|
|
out = self.conv1(x)
|
|
out = self.norm1(out)
|
|
out = self.relu(out)
|
|
|
|
out = self.conv2(out)
|
|
out = self.norm2(out)
|
|
|
|
if self.downsample is not None:
|
|
identity = self.downsample(x)
|
|
|
|
out += identity
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class Bottleneck(nn.Module):
|
|
expansion = 4
|
|
|
|
def __init__(self,
|
|
inplanes,
|
|
planes,
|
|
stride=1,
|
|
dilation=1,
|
|
downsample=None,
|
|
style='pytorch',
|
|
with_cp=False,
|
|
conv_cfg=None,
|
|
norm_cfg=dict(type='BN')):
|
|
"""Bottleneck block for ResNet.
|
|
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__()
|
|
assert style in ['pytorch', 'caffe']
|
|
|
|
self.inplanes = inplanes
|
|
self.planes = planes
|
|
self.stride = stride
|
|
self.dilation = dilation
|
|
self.style = style
|
|
self.with_cp = with_cp
|
|
self.conv_cfg = conv_cfg
|
|
self.norm_cfg = norm_cfg
|
|
|
|
if self.style == 'pytorch':
|
|
self.conv1_stride = 1
|
|
self.conv2_stride = stride
|
|
else:
|
|
self.conv1_stride = stride
|
|
self.conv2_stride = 1
|
|
|
|
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
|
|
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
|
|
self.norm3_name, norm3 = build_norm_layer(
|
|
norm_cfg, planes * self.expansion, postfix=3)
|
|
|
|
self.conv1 = build_conv_layer(
|
|
conv_cfg,
|
|
inplanes,
|
|
planes,
|
|
kernel_size=1,
|
|
stride=self.conv1_stride,
|
|
bias=False)
|
|
self.add_module(self.norm1_name, norm1)
|
|
self.conv2 = build_conv_layer(
|
|
conv_cfg,
|
|
planes,
|
|
planes,
|
|
kernel_size=3,
|
|
stride=self.conv2_stride,
|
|
padding=dilation,
|
|
dilation=dilation,
|
|
bias=False)
|
|
self.add_module(self.norm2_name, norm2)
|
|
self.conv3 = build_conv_layer(
|
|
conv_cfg,
|
|
planes,
|
|
planes * self.expansion,
|
|
kernel_size=1,
|
|
bias=False)
|
|
self.add_module(self.norm3_name, norm3)
|
|
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.downsample = downsample
|
|
|
|
@property
|
|
def norm1(self):
|
|
return getattr(self, 'bn1')
|
|
|
|
@property
|
|
def norm2(self):
|
|
return getattr(self, 'bn2')
|
|
|
|
@property
|
|
def norm3(self):
|
|
return getattr(self, 'bn3')
|
|
|
|
def _inner_forward(self, x):
|
|
identity = x
|
|
|
|
out = self.conv1(x)
|
|
out = getattr(self, 'bn1')(out)
|
|
out = self.relu(out)
|
|
|
|
out = self.conv2(out)
|
|
out = getattr(self, 'bn2')(out)
|
|
out = self.relu(out)
|
|
|
|
out = self.conv3(out)
|
|
out = getattr(self, 'bn3')(out)
|
|
|
|
if self.downsample is not None:
|
|
identity = self.downsample(x)
|
|
|
|
out += identity
|
|
|
|
return out
|
|
|
|
def forward(self, x):
|
|
|
|
out = self._inner_forward(x)
|
|
out = self.relu(out)
|
|
return out
|
|
|
|
|
|
def make_res_layer(block,
|
|
inplanes,
|
|
planes,
|
|
blocks,
|
|
stride=1,
|
|
dilation=1,
|
|
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,
|
|
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,
|
|
style=style,
|
|
with_cp=with_cp,
|
|
conv_cfg=conv_cfg,
|
|
norm_cfg=norm_cfg))
|
|
|
|
return nn.Sequential(*layers)
|
|
|
|
|
|
@BACKBONES.register_module
|
|
class ResNetJIT(nn.Module):
|
|
"""ResNet 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.
|
|
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 (stop grad and set eval mode).
|
|
-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 ResNet
|
|
>>> import torch
|
|
>>> self = ResNet(depth=18)
|
|
>>> 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, 64, 8, 8)
|
|
(1, 128, 4, 4)
|
|
(1, 256, 2, 2)
|
|
(1, 512, 1, 1)
|
|
"""
|
|
|
|
arch_settings = {
|
|
18: (BasicBlock, (2, 2, 2, 2)),
|
|
34: (BasicBlock, (3, 4, 6, 3)),
|
|
50: (Bottleneck, (3, 4, 6, 3)),
|
|
101: (Bottleneck, (3, 4, 23, 3)),
|
|
152: (Bottleneck, (3, 8, 36, 3))
|
|
}
|
|
|
|
def __init__(self,
|
|
depth,
|
|
in_channels=3,
|
|
num_stages=4,
|
|
strides=(1, 2, 2, 2),
|
|
dilations=(1, 1, 1, 1),
|
|
out_indices=(0, 1, 2, 3, 4),
|
|
style='pytorch',
|
|
frozen_stages=-1,
|
|
conv_cfg=None,
|
|
norm_cfg=dict(type='BN', requires_grad=True),
|
|
norm_eval=False,
|
|
with_cp=False,
|
|
zero_init_residual=False):
|
|
super(ResNetJIT, self).__init__()
|
|
if depth not in self.arch_settings:
|
|
raise KeyError('invalid depth {} for resnet'.format(depth))
|
|
self.depth = depth
|
|
self.num_stages = num_stages
|
|
assert num_stages >= 1 and num_stages <= 4
|
|
self.strides = strides
|
|
self.dilations = dilations
|
|
assert len(strides) == len(dilations) == num_stages
|
|
self.out_indices = out_indices
|
|
assert max(out_indices) < num_stages + 1
|
|
self.style = style
|
|
self.frozen_stages = frozen_stages
|
|
self.conv_cfg = conv_cfg
|
|
self.norm_cfg = norm_cfg
|
|
self.with_cp = with_cp
|
|
self.norm_eval = norm_eval
|
|
self.zero_init_residual = zero_init_residual
|
|
self.block, stage_blocks = self.arch_settings[depth]
|
|
self.stage_blocks = stage_blocks[:num_stages]
|
|
self.inplanes = 64
|
|
|
|
self._make_stem_layer(in_channels)
|
|
|
|
self.res_layers = nn.ModuleList()
|
|
for i, num_blocks in enumerate(self.stage_blocks):
|
|
stride = strides[i]
|
|
dilation = dilations[i]
|
|
planes = 64 * 2**i
|
|
res_layer = make_res_layer(
|
|
self.block,
|
|
self.inplanes,
|
|
planes,
|
|
num_blocks,
|
|
stride=stride,
|
|
dilation=dilation,
|
|
style=self.style,
|
|
with_cp=with_cp,
|
|
conv_cfg=conv_cfg,
|
|
norm_cfg=norm_cfg)
|
|
self.inplanes = planes * self.block.expansion
|
|
layer_name = 'layer{}'.format(i + 1)
|
|
self.res_layers.add_module(layer_name, res_layer)
|
|
|
|
self._freeze_stages()
|
|
|
|
self.feat_dim = self.block.expansion * 64 * 2**(
|
|
len(self.stage_blocks) - 1)
|
|
|
|
@property
|
|
def norm1(self):
|
|
return getattr(self, 'bn1')
|
|
|
|
def _make_stem_layer(self, in_channels):
|
|
self.conv1 = build_conv_layer(
|
|
self.conv_cfg,
|
|
in_channels,
|
|
64,
|
|
kernel_size=7,
|
|
stride=2,
|
|
padding=3,
|
|
bias=False)
|
|
self.norm1_name, norm1 = build_norm_layer(self.norm_cfg, 64, postfix=1)
|
|
self.bn1 = norm1
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
|
|
|
|
def _freeze_stages(self):
|
|
if self.frozen_stages >= 0:
|
|
self.norm1.eval()
|
|
for m in [self.conv1, self.norm1]:
|
|
for param in m.parameters():
|
|
param.requires_grad = False
|
|
|
|
for i in range(1, self.frozen_stages + 1):
|
|
m = getattr(self, 'layer{}'.format(i))
|
|
m.eval()
|
|
for param in m.parameters():
|
|
param.requires_grad = False
|
|
|
|
def init_weights(self):
|
|
for m in self.modules():
|
|
if isinstance(m, nn.Conv2d):
|
|
kaiming_init(m, mode='fan_in', nonlinearity='relu')
|
|
elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
|
|
constant_init(m, 1)
|
|
|
|
if self.zero_init_residual:
|
|
for m in self.modules():
|
|
if isinstance(m, Bottleneck):
|
|
constant_init(m.norm3, 0)
|
|
elif isinstance(m, BasicBlock):
|
|
constant_init(m.norm2, 0)
|
|
|
|
def forward(self, x: torch.Tensor) -> List[torch.Tensor]:
|
|
outs = []
|
|
x = self.conv1(x)
|
|
x = self.bn1(x)
|
|
x = self.relu(x) # r50: 64x128x128
|
|
if 0 in self.out_indices:
|
|
outs.append(x)
|
|
x = self.maxpool(x) # r50: 64x56x56
|
|
for i, res_layer in enumerate(self.res_layers):
|
|
x = res_layer(x)
|
|
if i + 1 in self.out_indices:
|
|
outs.append(x)
|
|
|
|
# r50: 1-256x56x56; 2-512x28x28; 3-1024x14x14; 4-2048x7x7
|
|
return outs
|
|
|
|
def train(self, mode=True):
|
|
super(ResNetJIT, 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()
|