本文介绍了Deep Layer Aggregation（DLA）模型，将聚合定义为网络不同层的组合，提出深度可聚合结构，通过迭代深层聚合（IDA）和分层深度聚合（HDA）融合特征。迁移了官方模型代码和预训练参数，验证了精度。还展示了模型细节、搭建、精度验证及训练示例，指出DLA能以较少参数和计算量获更高精度。
☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜
论文：Deep Layer Aggregation
官方实现：ucbdrive/dla
验证集数据处理：
# 图像后端: pil# 输入大小: 224x224transforms = T.Compose([
T.Resize(256, interpolation='bilinear'),
T.CenterCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])模型细节：
| Model | Model Name | Params (M) | FLOPs (G) | Top-1 (%) | Top-5 (%) | Pretrained Model |
|---|---|---|---|---|---|---|
| DLA-34 | dla_34 | 15.8 | 3.1 | 76.39 | 93.15 | Download |
| DLA-46-c | dla_46_c | 1.3 | 0.5 | 64.88 | 86.29 | Download |
| DLA-46x-c | dla_46x_c | 1.1 | 0.5 | 65.98 | 86.98 | Download |
| DLA-60 | dla_60 | 22.0 | 4.2 | 77.02 | 93.31 | Download |
| DLA-60x | dla_60x | 17.4 | 3.5 | 78.24 | 94.02 | Download |
| DLA-60x-c | dla_60x_c | 1.3 | 0.6 | 67.91 | 88.43 | Download |
| DLA-102 | dla_102 | 33.3 | 7.2 | 79.44 | 94.76 | Download |
| DLA-102x | dla_102x | 26.4 | 5.9 | 78.51 | 94.23 | Download |
| DLA-102x2 | dla_102x2 | 41.4 | 9.3 | 79.45 | 94.64 | Download |
| DLA-169 | dla_169 | 53.5 | 11.6 | 78.71 | 94.34 | Download |
x1，x2，，，xn代表n层，N是聚合结点。
N代表聚合节点。B代表一个卷积块。
σ是非线性激活。公式4是相对于公式3加了残差连接。
import mathimport paddleimport paddle.nn as nnimport paddle.nn.functional as Ffrom paddle.nn.initializer import Constant, Normal# 初始化zeros_ = Constant(value=0.)
ones_ = Constant(value=1.)# 占位层class Identity(nn.Layer):
def __init__(self):
super(Identity, self).__init__() def forward(self, input):
return input# DLA Basic 模块（ConvBNs + Residual）class DlaBasic(nn.Layer):
def __init__(self, inplanes, planes, stride=1, dilation=1, **cargs):
super(DlaBasic, self).__init__()
self.conv1 = nn.Conv2D(
inplanes, planes, kernel_size=3, stride=stride, padding=dilation, bias_attr=False, dilation=dilation)
self.bn1 = nn.BatchNorm2D(planes)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2D(
planes, planes, kernel_size=3, stride=1, padding=dilation, bias_attr=False, dilation=dilation)
self.bn2 = nn.BatchNorm2D(planes)
self.stride = stride def forward(self, x, residual=None):
if residual is None:
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out += residual
out = self.relu(out) return out# DLA Bottleneck 模块（ConvBNs + Residual）class DlaBottleneck(nn.Layer):
expansion = 2
def __init__(self, inplanes, outplanes, stride=1, dilation=1, cardinality=1, base_width=64):
super(DlaBottleneck, self).__init__()
self.stride = stride
mid_planes = int(math.floor(
outplanes * (base_width / 64)) * cardinality)
mid_planes = mid_planes // self.expansion
self.conv1 = nn.Conv2D(inplanes, mid_planes,
kernel_size=1, bias_attr=False)
self.bn1 = nn.BatchNorm2D(mid_planes)
self.conv2 = nn.Conv2D(
mid_planes, mid_planes, kernel_size=3, stride=stride, padding=dilation,
bias_attr=False, dilation=dilation, groups=cardinality)
self.bn2 = nn.BatchNorm2D(mid_planes)
self.conv3 = nn.Conv2D(mid_planes, outplanes,
kernel_size=1, bias_attr=False)
self.bn3 = nn.BatchNorm2D(outplanes)
self.relu = nn.ReLU() def forward(self, x, residual=None):
if residual is None:
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)
out += residual
out = self.relu(out) return out# DLA 根节点class DlaRoot(nn.Layer):
def __init__(self, in_channels, out_channels, kernel_size, residual):
super(DlaRoot, self).__init__()
self.conv = nn.Conv2D(
in_channels, out_channels, 1, stride=1, bias_attr=False, padding=(kernel_size - 1) // 2)
self.bn = nn.BatchNorm2D(out_channels)
self.relu = nn.ReLU()
self.residual = residual def forward(self, *x):
children = x
x = self.conv(paddle.concat(x, 1))
x = self.bn(x) if self.residual:
x += children[0]
x = self.relu(x) return x# DLA Tree（通过 Tree 的方式来组织模型网络）class DlaTree(nn.Layer):
def __init__(self, levels, block, in_channels, out_channels, stride=1,
dilation=1, cardinality=1, base_width=64,
level_root=False, root_dim=0, root_kernel_size=1, root_residual=False):
super(DlaTree, self).__init__() if root_dim == 0:
root_dim = 2 * out_channels if level_root:
root_dim += in_channels
self.downsample = nn.MaxPool2D(
stride, stride=stride) if stride > 1 else Identity()
self.project = Identity()
cargs = dict(dilation=dilation, cardinality=cardinality,
base_width=base_width) if levels == 1:
self.tree1 = block(in_channels, out_channels, stride, **cargs)
self.tree2 = block(out_channels, out_channels, 1, **cargs) if in_channels != out_channels:
self.project = nn.Sequential(
nn.Conv2D(in_channels, out_channels,
kernel_size=1, stride=1, bias_attr=False),
nn.BatchNorm2D(out_channels)) else:
cargs.update(dict(root_kernel_size=root_kernel_size,
root_residual=root_residual))
self.tree1 = DlaTree(
levels - 1, block, in_channels, out_channels, stride, root_dim=0, **cargs)
self.tree2 = DlaTree(
levels - 1, block, out_channels, out_channels, root_dim=root_dim + out_channels, **cargs) if levels == 1:
self.root = DlaRoot(root_dim, out_channels,
root_kernel_size, root_residual)
self.level_root = level_root
self.root_dim = root_dim
self.levels = levels def forward(self, x, residual=None, children=None):
children = [] if children is None else children
bottom = self.downsample(x)
residual = self.project(bottom) if self.level_root:
children.append(bottom)
x1 = self.tree1(x, residual) if self.levels == 1:
x2 = self.tree2(x1)
x = self.root(x2, x1, *children) else:
children.append(x1)
x = self.tree2(x1, children=children) return x# DLA 模型class DLA(nn.Layer):
def __init__(self, levels, channels, in_chans=3, cardinality=1,
base_width=64, block=DlaBottleneck, residual_root=False,
drop_rate=0.0, class_dim=1000, with_pool=True):
super(DLA, self).__init__()
self.channels = channels
self.class_dim = class_dim
self.with_pool = with_pool
self.cardinality = cardinality
self.base_width = base_width
self.drop_rate = drop_rate
self.base_layer = nn.Sequential(
nn.Conv2D(in_chans, channels[0], kernel_size=7,
stride=1, padding=3, bias_attr=False),
nn.BatchNorm2D(channels[0]),
nn.ReLU())
self.level0 = self._make_conv_level(
channels[0], channels[0], levels[0])
self.level1 = self._make_conv_level(
channels[0], channels[1], levels[1], stride=2)
cargs = dict(cardinality=cardinality,
base_width=base_width, root_residual=residual_root)
self.level2 = DlaTree(
levels[2], block, channels[1], channels[2], 2, level_root=False, **cargs)
self.level3 = DlaTree(
levels[3], block, channels[2], channels[3], 2, level_root=True, **cargs)
self.level4 = DlaTree(
levels[4], block, channels[3], channels[4], 2, level_root=True, **cargs)
self.level5 = DlaTree(
levels[5], block, channels[4], channels[5], 2, level_root=True, **cargs)
self.feature_info = [ # rare to have a meaningful stride 1 level
dict(num_chs=channels[0], reduction=1, module='level0'), dict(num_chs=channels[1], reduction=2, module='level1'), dict(num_chs=channels[2], reduction=4, module='level2'), dict(num_chs=channels[3], reduction=8, module='level3'), dict(num_chs=channels[4], reduction=16, module='level4'), dict(num_chs=channels[5], reduction=32, module='level5'),
]
self.num_features = channels[-1] if with_pool:
self.global_pool = nn.AdaptiveAvgPool2D(1) if class_dim > 0:
self.fc = nn.Conv2D(self.num_features, class_dim, 1) for m in self.sublayers(): if isinstance(m, nn.Conv2D):
n = m._kernel_size[0] * m._kernel_size[1] * m._out_channels
normal_ = Normal(mean=0.0, std=math.sqrt(2. / n))
normal_(m.weight) elif isinstance(m, nn.BatchNorm2D):
ones_(m.weight)
zeros_(m.bias) def _make_conv_level(self, inplanes, planes, convs, stride=1, dilation=1):
modules = [] for i in range(convs):
modules.extend([
nn.Conv2D(inplanes, planes, kernel_size=3, stride=stride if i == 0 else 1,
padding=dilation, bias_attr=False, dilation=dilation),
nn.BatchNorm2D(planes),
nn.ReLU()])
inplanes = planes return nn.Sequential(*modules) def forward_features(self, x):
x = self.base_layer(x)
x = self.level0(x)
x = self.level1(x)
x = self.level2(x)
x = self.level3(x)
x = self.level4(x)
x = self.level5(x) return x def forward(self, x):
x = self.forward_features(x) if self.with_pool:
x = self.global_pool(x) if self.drop_rate > 0.:
x = F.dropout(x, p=self.drop_rate, training=self.training) if self.class_dim > 0:
x = self.fc(x)
x = x.flatten(1) return xdef dla_34(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 2, 1),
channels=(16, 32, 64, 128, 256, 512),
block=DlaBasic,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla34.pdparams')
model.set_dict(params) return modeldef dla_46_c(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 2, 1),
channels=(16, 32, 64, 64, 128, 256),
block=DlaBottleneck,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla46_c.pdparams')
model.set_dict(params) return modeldef dla_46x_c(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 2, 1),
channels=(16, 32, 64, 64, 128, 256),
block=DlaBottleneck,
cardinality=32,
base_width=4,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla46x_c.pdparams')
model.set_dict(params) return modeldef dla_60x_c(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 3, 1),
channels=(16, 32, 64, 64, 128, 256),
block=DlaBottleneck,
cardinality=32,
base_width=4,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla60x_c.pdparams')
model.set_dict(params) return modeldef dla_60(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 3, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla60.pdparams')
model.set_dict(params) return modeldef dla_60x(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 2, 3, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
cardinality=32,
base_width=4,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla60x.pdparams')
model.set_dict(params) return modeldef dla_102(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 3, 4, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
residual_root=True,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla102.pdparams')
model.set_dict(params) return modeldef dla_102x(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 3, 4, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
cardinality=32,
base_width=4,
residual_root=True,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla102x.pdparams')
model.set_dict(params) return modeldef dla_102x2(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 1, 3, 4, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
cardinality=64,
base_width=4,
residual_root=True,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla102x2.pdparams')
model.set_dict(params) return modeldef dla_169(pretrained=False, **kwargs):
model = DLA(
levels=(1, 1, 2, 3, 5, 1),
channels=(16, 32, 128, 256, 512, 1024),
block=DlaBottleneck,
residual_root=True,
**kwargs
) if pretrained:
params = paddle.load('/home/aistudio/data/data78316/dla169.pdparams')
model.set_dict(params) return model# 解压数据集!mkdir ~/data/ILSVRC2012 !tar -xf ~/data/data68594/ILSVRC2012_img_val.tar -C ~/data/ILSVRC2012
import osimport cv2import numpy as npimport paddleimport paddle.vision.transforms as Tfrom PIL import Image# 构建数据集class ILSVRC2012(paddle.io.Dataset):
def __init__(self, root, label_list, transform, backend='pil'):
self.transform = transform
self.root = root
self.label_list = label_list
self.backend = backend
self.load_datas() def load_datas(self):
self.imgs = []
self.labels = [] with open(self.label_list, 'r') as f: for line in f:
img, label = line[:-1].split(' ')
self.imgs.append(os.path.join(self.root, img))
self.labels.append(int(label)) def __getitem__(self, idx):
label = self.labels[idx]
image = self.imgs[idx] if self.backend=='cv2':
image = cv2.imread(image) else:
image = Image.open(image).convert('RGB')
image = self.transform(image) return image.astype('float32'), np.array(label).astype('int64') def __len__(self):
return len(self.imgs)# 配置模型val_transforms = T.Compose([
T.Resize(256, interpolation='bilinear'),
T.CenterCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
model = dla_60(pretrained=True)
model = paddle.Model(model)
model.prepare(metrics=paddle.metric.Accuracy(topk=(1, 5)))# 配置数据集val_dataset = ILSVRC2012('data/ILSVRC2012', transform=val_transforms, label_list='data/data68594/val_list.txt', backend='pil')# 模型验证acc = model.evaluate(val_dataset, batch_size=128, num_workers=0, verbose=0)print(acc)/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:143: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations if data.dtype == np.object: /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dataloader/dataloader_iter.py:89: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations if isinstance(slot[0], (np.ndarray, np.bool, numbers.Number)): /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:77: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working return (isinstance(seq, collections.Sequence) and
# 导入 Paddleimport paddleimport paddle.nn as nnimport paddle.vision.transforms as Tfrom paddle.vision import Cifar100# 加载模型model = dla_60(pretrained=True, class_dim=100)# 使用高层 API 进行模型封装model = paddle.Model(model)# 配置优化器opt = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())# 配置损失函数loss = nn.CrossEntropyLoss()# 配置评价指标metric = paddle.metric.Accuracy(topk=(1, 5))# 模型准备model.prepare(optimizer=opt, loss=loss, metrics=metric)# 配置数据增广train_transforms = T.Compose([
T.Resize(256, interpolation='bilinear'),
T.RandomCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
val_transforms = T.Compose([
T.Resize(256, interpolation='bilinear'),
T.CenterCrop(224),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])# 配置数据集train_dataset = Cifar100(mode='train', transform=train_transforms, backend='pil')
val_dataset = Cifar100(mode='test', transform=val_transforms, backend='pil')# 模型微调model.fit(
train_data=train_dataset,
eval_data=val_dataset,
batch_size=64,
epochs=1,
eval_freq=1,
log_freq=1,
save_dir='save_models',
save_freq=1,
verbose=1,
drop_last=False,
shuffle=True,
num_workers=0)/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1303: UserWarning: Skip loading for fc.weight. fc.weight receives a shape [1000, 1024, 1, 1], but the expected shape is [100, 1024, 1, 1].
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1303: UserWarning: Skip loading for fc.bias. fc.bias receives a shape [1000], but the expected shape is [100].
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
Cache file /home/aistudio/.cache/paddle/dataset/cifar/cifar-100-python.tar.gz not found, downloading https://dataset.bj.bcebos.com/cifar/cifar-100-python.tar.gz
Begin to download
Download finishedThe loss value printed in the log is the current step, and the metric is the average value of previous step. Epoch 1/1
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/nn/layer/norm.py:648: UserWarning: When training, we now always track global mean and variance. "When training, we now always track global mean and variance.")
step 782/782 [==============================] - loss: 2.2643 - acc_top1: 0.3284 - acc_top5: 0.6364 - 328ms/step save checkpoint at /home/aistudio/save_models/0 Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 157/157 [==============================] - loss: 2.3870 - acc_top1: 0.4577 - acc_top5: 0.7807 - 171ms/step Eval samples: 10000 save checkpoint at /home/aistudio/save_models/final
以上就是基于 Paddle2.0 实现 DLA 模型的详细内容，更多请关注php中文网其它相关文章！
每个人都需要一台速度更快、更稳定的 PC。随着时间的推移，垃圾文件、旧注册表数据和不必要的后台进程会占用资源并降低性能。幸运的是，许多工具可以让 Windows 保持平稳运行。
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
493
收藏
