mmdetection源码解读（五）
前面我们零散的了解了mmdetection用到的一些python和PyTorch的知识。
现在我们开始深入算法模型来学习，这个模块我们尝试自定义一个se_resnet50来学习自定义backbone.
在mmdetection/mmdet/models/backbone文件下创建一个senet.py的python文件。
"""
ResNet code gently borrowed from
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
"""
from __future__ import print_function, division, absolute_import
from collections import OrderedDict
from ..registry import BACKBONES
from mmcv.runner import load_checkpoint
import logging
from mmcv.cnn import constant_init, kaiming_init
import math
import torch.nn as nn
from torch.utils import model_zoo
__all__ = ['SENet', 'senet154', 'se_resnet50', 'se_resnet101', 'se_resnet152',
'se_resnext50_32x4d', 'se_resnext101_32x4d']
pretrained_settings = {
'senet154': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/senet154-c7b49a05.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnet50': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet50-ce0d4300.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnet101': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet101-7e38fcc6.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnet152': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet152-d17c99b7.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnext50_32x4d': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext50_32x4d-a260b3a4.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnext101_32x4d': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
}
class SEModule(nn.Module):
def __init__(self, channels, reduction):
super(SEModule, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc1 = nn.Conv2d(channels, channels // reduction, kernel_size=1,
padding=0)
self.relu = nn.ReLU(inplace=True)
self.fc2 = nn.Conv2d(channels // reduction, channels, kernel_size=1,
padding=0)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
module_input = x
x = self.avg_pool(x)
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
x = self.sigmoid(x)
return module_input * x
class Bottleneck(nn.Module):
"""
Base class for bottlenecks that implements `forward()` method.
"""
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out = self.se_module(out) + residual
out = self.relu(out)
return out
class SEBottleneck(Bottleneck):
"""
Bottleneck for SENet154.
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None):
super(SEBottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes * 2, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes * 2)
self.conv2 = nn.Conv2d(planes * 2, planes * 4, kernel_size=3,
stride=stride, padding=1, groups=groups,
bias=False)
self.bn2 = nn.BatchNorm2d(planes * 4)
self.conv3 = nn.Conv2d(planes * 4, planes * 4, kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.se_module = SEModule(planes * 4, reduction=reduction)
self.downsample = downsample
self.stride = stride
class SEResNetBottleneck(Bottleneck):
"""
ResNet bottleneck with a Squeeze-and-Excitation module. It follows Caffe
implementation and uses `stride=stride` in `conv1` and not in `conv2`
(the latter is used in the torchvision implementation of ResNet).
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None):
super(SEResNetBottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False,
stride=stride)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1,
groups=groups, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.se_module = SEModule(planes * 4, reduction=reduction)
self.downsample = downsample
self.stride = stride
class SEResNeXtBottleneck(Bottleneck):
"""
ResNeXt bottleneck type C with a Squeeze-and-Excitation module.
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None, base_width=4):
super(SEResNeXtBottleneck, self).__init__()
width = math.floor(planes * (base_width / 64)) * groups
self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, bias=False,
stride=1)
self.bn1 = nn.BatchNorm2d(width)
self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride,
padding=1, groups=groups, bias=False)
self.bn2 = nn.BatchNorm2d(width)
self.conv3 = nn.Conv2d(width, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.se_module = SEModule(planes * 4, reduction=reduction)
self.downsample = downsample
self.stride = stride
bottleneck_dic = {
'SEBottleneck': SEBottleneck,
'SEResNetBottleneck': SEResNetBottleneck,
'SEResNeXtBottleneck': SEResNeXtBottleneck
}
@BACKBONES.register_module
class SENet(nn.Module):
def __init__(self, block, layers, groups, reduction, dropout_p=0.2,
inplanes=128, input_3x3=True, downsample_kernel_size=3,
downsample_padding=1,norm_eval=True, frozen_stages=-1, zero_init_residual=True, num_classes=1000):
"""
Parameters
----------
block (nn.Module): Bottleneck class.
- For SENet154: SEBottleneck
- For SE-ResNet models: SEResNetBottleneck
- For SE-ResNeXt models: SEResNeXtBottleneck
layers (list of ints): Number of residual blocks for 4 layers of the
network (layer1...layer4).
groups (int): Number of groups for the 3x3 convolution in each
bottleneck block.
- For SENet154: 64
- For SE-ResNet models: 1
- For SE-ResNeXt models: 32
reduction (int): Reduction ratio for Squeeze-and-Excitation modules.
- For all models: 16
dropout_p (float or None): Drop probability for the Dropout layer.
If `None` the Dropout layer is not used.
- For SENet154: 0.2
- For SE-ResNet models: None
- For SE-ResNeXt models: None
inplanes (int): Number of input channels for layer1.
- For SENet154: 128
- For SE-ResNet models: 64
- For SE-ResNeXt models: 64
input_3x3 (bool): If `True`, use three 3x3 convolutions instead of
a single 7x7 convolution in layer0.
- For SENet154: True
- For SE-ResNet models: False
- For SE-ResNeXt models: False
downsample_kernel_size (int): Kernel size for downsampling convolutions
in layer2, layer3 and layer4.
- For SENet154: 3
- For SE-ResNet models: 1
- For SE-ResNeXt models: 1
downsample_padding (int): Padding for downsampling convolutions in
layer2, layer3 and layer4.
- For SENet154: 1
- For SE-ResNet models: 0
- For SE-ResNeXt models: 0
num_classes (int): Number of outputs in `last_linear` layer.
- For all models: 1000
"""
super(SENet, self).__init__()
block = bottleneck_dic[block]
self.inplanes = inplanes
self.frozen_stages = frozen_stages
self.norm_eval = norm_eval
self.zero_init_residual = zero_init_residual
if input_3x3:
layer0_modules = [
('conv1', nn.Conv2d(3, 64, 3, stride=2, padding=1,
bias=False)),
('bn1', nn.BatchNorm2d(64)),
('relu1', nn.ReLU(inplace=True)),
('conv2', nn.Conv2d(64, 64, 3, stride=1, padding=1,
bias=False)),
('bn2', nn.BatchNorm2d(64)),
('relu2', nn.ReLU(inplace=True)),
('conv3', nn.Conv2d(64, inplanes, 3, stride=1, padding=1,
bias=False)),
('bn3', nn.BatchNorm2d(inplanes)),
('relu3', nn.ReLU(inplace=True)),
]
else:
layer0_modules = [
('conv1', nn.Conv2d(3, inplanes, kernel_size=7, stride=2,
padding=3, bias=False)),
('bn1', nn.BatchNorm2d(inplanes)),
('relu1', nn.ReLU(inplace=True)),
]
# To preserve compatibility with Caffe weights `ceil_mode=True`
# is used instead of `padding=1`.
layer0_modules.append(('pool', nn.MaxPool2d(3, stride=2,
ceil_mode=True)))
self.layer0 = nn.Sequential(OrderedDict(layer0_modules))
self.layer1 = self._make_layer(
block,
planes=64,
blocks=layers[0],
groups=groups,
reduction=reduction,
downsample_kernel_size=1,
downsample_padding=0
)
self.layer2 = self._make_layer(
block,
planes=128,
blocks=layers[1],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
self.layer3 = self._make_layer(
block,
planes=256,
blocks=layers[2],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
self.layer4 = self._make_layer(
block,
planes=512,
blocks=layers[3],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
# self.avg_pool = nn.AvgPool2d(7, stride=1)
# self.dropout = nn.Dropout(dropout_p) if dropout_p is not None else None
# self.last_linear = nn.Linear(512 * block.expansion, num_classes)
self._freeze_stages()
def _freeze_stages(self):
if self.frozen_stages >= 0:
for m in [self.layer0]:
m.eval()
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, 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, nn.BatchNorm2d):
constant_init(m, 1)
if self.zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
constant_init(m.bn3, 0)
else:
raise TypeError('pretrained must be a str or None')
def _make_layer(self, block, planes, blocks, groups, reduction, stride=1,
downsample_kernel_size=1, downsample_padding=0):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=downsample_kernel_size, stride=stride,
padding=downsample_padding, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, groups, reduction, stride,
downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, groups, reduction))
return nn.Sequential(*layers)
def features(self, x):
outputs = []
x = self.layer0(x)
x = self.layer1(x)
outputs.append(x)
x = self.layer2(x)
outputs.append(x)
x = self.layer3(x)
outputs.append(x)
x = self.layer4(x)
outputs.append(x)
return x, outputs
'''
def logits(self, x):
x = self.avg_pool(x)
if self.dropout is not None:
x = self.dropout(x)
x = x.view(x.size(0), -1)
x = self.last_linear(x)
return x
'''
def forward(self, x):
x, outputs = self.features(x)
# x = self.logits(x)
return outputs # x
def train(self, mode=True):
super(SENet, 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, (nn.BatchNorm2d)):
m.eval()
def initialize_pretrained_model(model, num_classes, settings):
assert num_classes == settings['num_classes'], \
'num_classes should be {}, but is {}'.format(
settings['num_classes'], num_classes)
model.load_state_dict(model_zoo.load_url(settings['url']))
model.input_space = settings['input_space']
model.input_size = settings['input_size']
model.input_range = settings['input_range']
model.mean = settings['mean']
model.std = settings['std']
def senet154(num_classes=1000, pretrained='imagenet'):
model = SENet(SEBottleneck, [3, 8, 36, 3], groups=64, reduction=16,
dropout_p=0.2, num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['senet154'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet50(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 4, 6, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet50'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet101(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 4, 23, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet101'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet152(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 8, 36, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet152'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnext50_32x4d(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnext50_32x4d'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnext101_32x4d(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnext101_32x4d'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model上面就是senet.py的内容了。
主要是下面这里，自定义好类后，需要进行注册。
@BACKBONES.register_module
class SENet(nn.Module):还有__init__.py文件里也需要添加相应的模块
from .hrnet import HRNet
from .resnet import ResNet, make_res_layer
from .resnext import ResNeXt
from .ssd_vgg import SSDVGG
from .senet import SENet
__all__ = ['SENet','ResNet', 'make_res_layer', 'ResNeXt', 'SSDVGG', 'HRNet']
最后在mmdetection/configs/pascal_voc目录下创建配置文件faster_rcnn_ser50_fpn_1x_voc0712.py。
# model settings
model = dict(
type='FasterRCNN',
#pretrained='torchvision://resnet50',
pretrained='/home/yyf/mmdetection/checkpoints/se_resnet50-ce0d4300.pth',
backbone=dict(
type='SENet',
block='SEResNetBottleneck',
layers=[3, 4, 6, 3],
groups=1,
reduction=16,
dropout_p=None,
inplanes=64,
input_3x3=False,
downsample_kernel_size=1,
downsample_padding=0,
frozen_stages=1
#depth=50,
#num_stages=4,
#out_indices=(0, 1, 2, 3),
#style='pytorch'
),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=21,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
)
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1000, 600),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[3]) # actual epoch = 3 * 3 = 9
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 4 # actual epoch = 4 * 3 = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/faster_rcnn_ser50_fpn_1x_voc0712'
load_from = None
resume_from = None
workflow = [('train', 1)]上面都做好后，还要重新运行python setup.py develop重新编译安装。
完成后就可以愉快的玩耍了。
参考内容：参考