从keras的keras_applications的文件夹内可以找到内置模型的源代码

Kera的应用模块Application提供了带有预训练权重的Keras模型,这些模型可以用来进行预测、特征提取和finetune

应用于图像分类的模型,权重训练自ImageNet: Xception VGG16 VGG19 ResNet50 InceptionV3InceptionResNetV2 * MobileNet densenet

densenet的keras源代码如下:

"""DenseNet models for Keras.

# Reference paper

- [Densely Connected Convolutional Networks]
(https://arxiv.org/abs/1608.06993) (CVPR 2017 Best Paper Award) # Reference implementation - [Torch DenseNets]
(https://github.com/liuzhuang13/DenseNet/blob/master/models/densenet.lua)
- [TensorNets]
(https://github.com/taehoonlee/tensornets/blob/master/tensornets/densenets.py)
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function import os from . import get_keras_submodule backend = get_keras_submodule('backend')
engine = get_keras_submodule('engine')
layers = get_keras_submodule('layers')
models = get_keras_submodule('models')
keras_utils = get_keras_submodule('utils') from . import imagenet_utils
from .imagenet_utils import decode_predictions
from .imagenet_utils import _obtain_input_shape BASE_WEIGTHS_PATH = (
'https://github.com/fchollet/deep-learning-models/'
'releases/download/v0.8/')
DENSENET121_WEIGHT_PATH = (
BASE_WEIGTHS_PATH +
'densenet121_weights_tf_dim_ordering_tf_kernels.h5')
DENSENET121_WEIGHT_PATH_NO_TOP = (
BASE_WEIGTHS_PATH +
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5')
DENSENET169_WEIGHT_PATH = (
BASE_WEIGTHS_PATH +
'densenet169_weights_tf_dim_ordering_tf_kernels.h5')
DENSENET169_WEIGHT_PATH_NO_TOP = (
BASE_WEIGTHS_PATH +
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5')
DENSENET201_WEIGHT_PATH = (
BASE_WEIGTHS_PATH +
'densenet201_weights_tf_dim_ordering_tf_kernels.h5')
DENSENET201_WEIGHT_PATH_NO_TOP = (
BASE_WEIGTHS_PATH +
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5') def dense_block(x, blocks, name):
"""A dense block. # Arguments
x: input tensor.
blocks: integer, the number of building blocks.
name: string, block label. # Returns
output tensor for the block.
"""
for i in range(blocks):
x = conv_block(x, 32, name=name + '_block' + str(i + 1))
return x def transition_block(x, reduction, name):
"""A transition block. # Arguments
x: input tensor.
reduction: float, compression rate at transition layers.
name: string, block label. # Returns
output tensor for the block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_bn')(x)
x = layers.Activation('relu', name=name + '_relu')(x)
x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction), 1,
use_bias=False,
name=name + '_conv')(x)
x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
return x def conv_block(x, growth_rate, name):
"""A building block for a dense block. # Arguments
x: input tensor.
growth_rate: float, growth rate at dense layers.
name: string, block label. # Returns
Output tensor for the block.
"""
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x1 = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name=name + '_0_bn')(x)
x1 = layers.Activation('relu', name=name + '_0_relu')(x1)
x1 = layers.Conv2D(4 * growth_rate, 1,
use_bias=False,
name=name + '_1_conv')(x1)
x1 = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name=name + '_1_bn')(x1)
x1 = layers.Activation('relu', name=name + '_1_relu')(x1)
x1 = layers.Conv2D(growth_rate, 3,
padding='same',
use_bias=False,
name=name + '_2_conv')(x1)
x = layers.Concatenate(axis=bn_axis, name=name + '_concat')([x, x1])
return x def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture. Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`. # Arguments
blocks: numbers of building blocks for the four dense layers.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified. # Returns
A Keras model instance. # Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000') # Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=221,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights) if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = layers.Activation('relu', name='conv1/relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1')(x) x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5') x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='bn')(x) if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = engine.get_source_inputs(input_tensor)
else:
inputs = img_input # Create model.
if blocks == [6, 12, 24, 16]:
model = models.Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = models.Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = models.Model(inputs, x, name='densenet201')
else:
model = models.Model(inputs, x, name='densenet') # Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = keras_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = keras_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = keras_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = keras_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = keras_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='50662582284e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = keras_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights) return model def DenseNet121(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 24, 16],
include_top, weights,
input_tensor, input_shape,
pooling, classes) def DenseNet169(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 32, 32],
include_top, weights,
input_tensor, input_shape,
pooling, classes) def DenseNet201(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
return DenseNet([6, 12, 48, 32],
include_top, weights,
input_tensor, input_shape,
pooling, classes) def preprocess_input(x, data_format=None):
"""Preprocesses a numpy array encoding a batch of images. # Arguments
x: a 3D or 4D numpy array consists of RGB values within [0, 255].
data_format: data format of the image tensor. # Returns
Preprocessed array.
"""
return imagenet_utils.preprocess_input(x, data_format, mode='torch') setattr(DenseNet121, '__doc__', DenseNet.__doc__)
setattr(DenseNet169, '__doc__', DenseNet.__doc__)
setattr(DenseNet201, '__doc__', DenseNet.__doc__)

从keras导入densenet模型需要以下代码

from keras.applications.densenet import DenseNet201,preprocess_input

#base_model = DenseNet(weights='imagenet', include_top=False)
base_model = DenseNet201(weights=None, include_top=False) x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(6941, activation='sigmoid')(x)
model = Model(inputs=base_model.input, outputs=predictions) model.summary()

使用keras导入densenet模型的更多相关文章

  1. PV3D学习笔记-导入DAE模型

      网上关于PV3D导入DAE模型的例子都非常多,可惜我研究了半天,一个都没成功,或者是破面问题,或者是贴图不显示,再或者贴图乱掉了.今天晚上终于搞定,心得发上来. 制作模型的软件是SketchUp ...

  2. Unity3D游戏开发从零单排(五) - 导入CS模型到Unity3D

    游戏动画基础 Animation组件 Animation组件是对于老的动画系统来说的. 老的动画形同相应的动画就是clip,每一个运动都是一段单独的动画,使用Play()或CrossFade(),直接 ...

  3. keras训练cnn模型时loss为nan

    keras训练cnn模型时loss为nan 1.首先记下来如何解决这个问题的:由于我代码中 model.compile(loss='categorical_crossentropy', optimiz ...

  4. keras中的模型保存和加载

    tensorflow中的模型常常是protobuf格式,这种格式既可以是二进制也可以是文本.keras模型保存和加载与tensorflow不同,keras中的模型保存和加载往往是保存成hdf5格式. ...

  5. opengl导入obj模型

    在经过查阅各种资料以及各种bug之后,终于成功的实现了导入基本的obj模型. 首相介绍一下什么是obj模型 一.什么是OBJ模型 obj文件实际上是一个文本文档,主要有以下数据,一般可以通过blend ...

  6. Keras实践:模型可视化

    Keras实践:模型可视化 安装Graphviz 官方网址为:http://www.graphviz.org/.我使用的是mac系统,所以我分享一下我使用时遇到的坑. Mac安装时在终端中执行: br ...

  7. Keras Sequential顺序模型

    keras是基于tensorflow封装的的高级API,Keras的优点是可以快速的开发实验,它能够以TensorFlow, CNTK, 或者 Theano 作为后端运行. 模型构建 最简单的模型是  ...

  8. Unity 3d导入3dMax模型 产生若干问题

    Unity 3d导入3dMax模型 会产生若干问题,按照官方 的说明,将max 模型导成fbx文件 导入untiy似乎也不能解决 1.x轴向偏转3dmax模型导入后自动有一个x轴270度的偏转,巧合的 ...

  9. scikit-learn系列之如何存储和导入机器学习模型

    scikit-learn系列之如何存储和导入机器学习模型   如何存储和导入机器学习模型 找到一个准确的机器学习模型,你的项目并没有完成.本文中你将学习如何使用scikit-learn来存储和导入机器 ...

随机推荐

  1. 6.824 Lab 5: Caching Extents

    Introduction In this lab you will modify YFS to cache extents, reducing the load on the extent serve ...

  2. git+gitolite+cgit+apache on Ubuntu

    git+gitolite+cgit+apache on Ubuntu Just record, do *NOT* copy-paste. git+gitolite sudo apt-get insta ...

  3. SpringBoot thymeleaf模板版本,thymeleaf模板更换版本

    SpringBoot thymeleaf模板版本 thymeleaf模板更换版本 修改thymeleaf模板版本 ================================ ©Copyright ...

  4. Scala单例对象和伴生对象

    1.Scala单例对象 Scala单例对象是十分重要的,没有像在Java一样,有静态类.静态成员.静态方法,但是Scala提供了object对象,这个object对象类似于Java的静态类,它的成员. ...

  5. hive-数据模型

    hive支持四种数据模型 • external table• table• partition• bucket 为了避免table名称冲突,hive用database作为顶层域名,如果不设定datab ...

  6. 使用Bind搭建DNS服务

    DNS域名解析服务(Domain Name System)是用于解析域名与IP地址对应关系的服务,功能上可以实现正向解析与反向解析: 正向解析:根据主机名(域名)查找对应的IP地址. 反向解析:根据I ...

  7. ie11中报SCRIPT1003: 缺少 ':'的错误?

    兼容性?IE的兼容性…… 由于“叶叶综合征发作”,导致有段时间都在自我否定中,故而引发一系列的不美好.幸好,自己还有超强的恢复能力,一切都在往好的方向发展吧. 直接进入 “可怕的IE兼容”主题: 第一 ...

  8. 阿里云CentOS7挂载SSD云盘的方法

    https://bbs.aliyun.com/read/151152.html 阿里云购买的第2块云盘默认是不自动挂载的,需要手动配置挂载上. 1.查看SSD云盘 sudo fdisk -l Disk ...

  9. vc下项目的头文件包含目录以及库导入预计库目录设置

    1.包含目录:include 头文件包含目录设置: project->setting->C/C++->常规: Additional include directories(附加包含目 ...

  10. Matlab——filter函数用法

    filter:滤波函数,可用来解差分方程. y = filter(b,a,X) [y,zf] = filter(b,a,X) [y,zf] = filter(b,a,X,zi) y = filter( ...