keras中resnet101的权重和模型架构

最新推荐文章于 2025-03-07 11:22:42 发布
最新推荐文章于 2025-03-07 11:22:42 发布
阅读量1.2k 收藏
点赞数 1
分类专栏： keras 文章标签： keras
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_27009517/article/details/110437564
版权
本文深入探讨了Keras库中的ResNet101模型，详细介绍了其权重配置和架构特点，提供了模型预训练权重的下载链接。

摘要生成于 C知道 ，由 DeepSeek-R1 满血版支持， 前往体验 >

resnet101

https://github.com/keras-team/keras-applications/releases/download/resnet/resnet101_weights_tf_dim_ordering_tf_kernels.h5

import tensorflow as tf
import numpy as np
# import keras


import keras.layers as KL
import keras.models as KM
import keras

import os
# os.environ['CUDA_DEVICES_VISIBLE'] = '1'
print(keras.__version__)



from keras.applications.resnet import ResNet101
# from keras.applications.resnet import ResNet152
# from keras.applications.resnet50 import ResNet50



input_image = KL.Input(shape=[512, 512, 3], name="input_image")

resnet50 = ResNet101(input_tensor=input_image, include_top=True)
# conv5_block1_1_conv
x = resnet50.get_layer('probs').output  # block5_pool  max_pool  conv5_block1_1_conv

# resnet50.summery(0)
inputs = [input_image]
outputs = [x]

model = KM.Model(inputs, outputs, name='ctpn')
model.summary()

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_image (InputLayer)        (None, 512, 512, 3)  0                                            
__________________________________________________________________________________________________
conv1_pad (ZeroPadding2D)       (None, 518, 518, 3)  0           input_image[0][0]                
__________________________________________________________________________________________________
conv1_conv (Conv2D)             (None, 256, 256, 64) 9472        conv1_pad[0][0]                  
__________________________________________________________________________________________________
conv1_bn (BatchNormalization)   (None, 256, 256, 64) 256         conv1_conv[0][0]                 
__________________________________________________________________________________________________
conv1_relu (Activation)         (None, 256, 256, 64) 0           conv1_bn[0][0]                   
__________________________________________________________________________________________________
pool1_pad (ZeroPadding2D)       (None, 258, 258, 64) 0           conv1_relu[0][0]                 
__________________________________________________________________________________________________
pool1_pool (MaxPooling2D)       (None, 128, 128, 64) 0           pool1_pad[0][0]                  
__________________________________________________________________________________________________
conv2_block1_1_conv (Conv2D)    (None, 128, 128, 64) 4160        pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_1_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_1_relu (Activation (None, 128, 128, 64) 0           conv2_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_2_conv (Conv2D)    (None, 128, 128, 64) 36928       conv2_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_relu (Activation (None, 128, 128, 64) 0           conv2_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_0_conv (Conv2D)    (None, 128, 128, 256 16640       pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_3_conv (Conv2D)    (None, 128, 128, 256 16640       conv2_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_0_bn (BatchNormali (None, 128, 128, 256 1024        conv2_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_3_bn (BatchNormali (None, 128, 128, 256 1024        conv2_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_add (Add)          (None, 128, 128, 256 0           conv2_block1_0_bn[0][0]          
                                                                 conv2_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_out (Activation)   (None, 128, 128, 256 0           conv2_block1_add[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_conv (Conv2D)    (None, 128, 128, 64) 16448       conv2_block1_out[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_1_relu (Activation (None, 128, 128, 64) 0           conv2_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_2_conv (Conv2D)    (None, 128, 128, 64) 36928       conv2_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_relu (Activation (None, 128, 128, 64) 0           conv2_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_3_conv (Conv2D)    (None, 128, 128, 256 16640       conv2_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_3_bn (BatchNormali (None, 128, 128, 256 1024        conv2_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_add (Add)          (None, 128, 128, 256 0           conv2_block1_out[0][0]           
                                                                 conv2_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_out (Activation)   (None, 128, 128, 256 0           conv2_block2_add[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_conv (Conv2D)    (None, 128, 128, 64) 16448       conv2_block2_out[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_1_relu (Activation (None, 128, 128, 64) 0           conv2_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_2_conv (Conv2D)    (None, 128, 128, 64) 36928       conv2_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_bn (BatchNormali (None, 128, 128, 64) 256         conv2_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_relu (Activation (None, 128, 128, 64) 0           conv2_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_3_conv (Conv2D)    (None, 128, 128, 256 16640       conv2_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_3_bn (BatchNormali (None, 128, 128, 256 1024        conv2_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_add (Add)          (None, 128, 128, 256 0           conv2_block2_out[0][0]           
                                                                 conv2_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_out (Activation)   (None, 128, 128, 256 0           conv2_block3_add[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_conv (Conv2D)    (None, 64, 64, 128)  32896       conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_bn (BatchNormali (None, 64, 64, 128)  512         conv3_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_1_relu (Activation (None, 64, 64, 128)  0           conv3_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_2_conv (Conv2D)    (None, 64, 64, 128)  147584      conv3_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_bn (BatchNormali (None, 64, 64, 128)  512         conv3_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_relu (Activation (None, 64, 64, 128)  0           conv3_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_0_conv (Conv2D)    (None, 64, 64, 512)  131584      conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_3_conv (Conv2D)    (None, 64, 64, 512)  66048       conv3_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_0_bn (BatchNormali (None, 64, 64, 512)  2048        conv3_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_3_bn (BatchNormali (None, 64, 64, 512)  2048        conv3_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_add (Add)          (None, 64, 64, 512)  0           conv3_block1_0_bn[0][0]          
                                                                 conv3_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_out (Activation)   (None, 64, 64, 512)  0           conv3_block1_add[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_conv (Conv2D)    (None, 64, 64, 128)  65664       conv3_block1_out[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_bn (BatchNormali (None, 64, 64, 128)  512         conv3_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_1_relu (Activation (None, 64, 64, 128)  0           conv3_block2_1_bn[
最低0.47元/天 解锁文章
keras中resnet101的模型架构
qq_27009517的博客
12-02 720
import keras.layers as KL import keras.models as KM import keras import os os.environ['CUDA_DEVICES_VISIBLE'] = '1' print(keras.__version__) from keras.applications.resnet import ResNet101 input_image = KL.Input(shape=[512, 512, 3], name="input_image..
经典神经网络resnet101预训练权重文件
01-26
经典神经网络resnet101预训练权重文件
ResNet101深度残差网络架构解析与技术实践
最新发布
AI
03-07 968
本文系统解析了ResNet101的网络架构设计理念与实现细节，通过理论分析与少量关键代码展示，揭示了深度残差网络的核心创新。实验数据表明，ResNet101在准确率与计算效率之间取得了良好平衡，至今仍是计算机视觉领域的重要基准模型。在计算机视觉领域，卷积神经网络（CNN）的深度与模型性能之间存在着密切的关联。ImageNet竞赛数据显示，当网络深度超过30层时，传统CNN的top-5错误率开始呈现不降反升的异常现象。这一发现直接催生了残差学习理论的诞生。：实验证明，56层网络的训练误差反而高于20层网络。
keras网络权重
04-28
重要的神经网络keras版本的权重，预训练好的网络参数适用于迁移学习。 inception_v3_weights_tf_dim_ordering_tf_kernels.h5；inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5； music_tagger_crnn_weights_tf_kernels_tf_dim_ordering.h5； music_tagger_crnn_weights_tf_kernels_th_dim_ordering.h5； resnet50_weights_tf_dim_ordering_tf_kernels.h5； resnet50_weights_th_dim_ordering_th_kernels_notop.h5； vgg16_weights_tf_dim_ordering_tf_kernels.h5； vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5； vgg19_weights_tf_dim_ordering_tf_kernels.h5； vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5； xception_weights_tf_dim_ordering_tf_kernels.h5； xception_weights_tf_dim_ordering_tf_kernels_notop.h5。
基于ResNet101的模型结构：ResNet101-ImageNet-CNTK
10-24
基于ResNet101的模型结构：ResNet101_ImageNet_CNTK
resnet101预训练模型.zip（pytorch版本）
08-02
有能力和有耐心的可以去这里下载: https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
keras中resnet50的权重和模型架构
qq_27009517的博客
12-01 2023
resnet50 https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5 from keras.applications.resnet50 import ResNet50 input_image = KL.Input(shape=[512, 512, 3], name="input_image") resnet5
keras中resnet152的权重和模型架构
qq_27009517的博客
12-01 1172
文章目录resnet152 resnet152 https://github.com/keras-team/keras-applications/releases/download/resnet/resnet152_weights_tf_dim_ordering_tf_kernels.h5 import keras.layers as KL import keras.models as KM import keras import os # os.environ['CUDA_DEVICES_VISIBL
keras-resnet：用于深度残差网络的Keras软件包
02-06
总的来说，`keras-resnet` 是一个强大的工具，它使深度学习从业者能够轻松地在Keras中构建和训练ResNets，利用这些先进的网络架构解决各种计算机视觉问题，如图像分类、目标检测和语义分割等。通过结合数据增强、...
使用TensorFlow和Keras对以ResNet50模型进行微调
heeheeai的博客
06-08 1499
以下是使用ResNet50进行微调以识别特定的新东西的代码演示。将使用TensorFlow和Keras进行这个任务。数据集下载地址，解压到工程里面去： 原始代码：​ ``` 解析 安装必要的库： 导入库： 加载ResNet50模型，并去掉顶层： 添加自定义顶层： 冻结base_model的所有卷积层： 编译模型： 准备数据： 假设数据存储在和中，并且每个类有一个文件夹。 训练模型： 解冻部分或全部的卷积层并继续训练： 在这段代码中，“添加自定义顶层”是指在预训练的R
resnet101预训练模型.zip
07-12
resnet 101 pytorch 预训练模型，官网不太好下载，下载速度慢我把这个下好以后上传上来了。主要是用于加载预训练的权重。
ResNet-101 网络的深度学习工具箱模型：用于图像分类的预训练 Resnet-101 网络模型-matlab开发
05-31
ResNet-101 是一个预训练模型，已经在 ImageNet 数据库的一个子集上进行了训练。 该模型在超过一百万张图像上进行训练，共有 347 层，对应于 101 层残差网络，可以将图像分为 1000 个对象类别（例如键盘、鼠标、铅笔和许多动物）。 从您的操作系统或 MATLAB 中打开 resnet101.mlpkginstall 文件将启动您拥有的版本的安装过程。 该mlpkginstall文件可用于R2017b及更高版本。 用法示例： % 访问训练好的模型净 = resnet101(); % 查看架构细节网络层% 读取图像进行分类I = imread('peppers.png'); % 调整图片大小sz = net.Layers(1).InputSize I = I(1:sz(1),1:sz(2),1:sz(3)); % 使用 Resnet-101 对图像进行分类标签 = 分类（
resnet101 caffe 模型
05-21
残差resnet网络 caffe resnet101Imagenet pre-trained模型
resnet101_weights_tf_dim_ordering_tf_kernels.h5
11-11
由于国内网被档，在迁移学习的时候模型下载出错，这里提供在最常用的resnet模型权重下载，下载后直接放入模型文件夹即可使用，如有疑问直接私聊我，另在我博客也写了如何实现keras-resnet101网络的迁移学习，欢迎大家观看。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。
pytorch resnet 101 模型参数数据
12-29
pytorch resnet 101 模型参数数据 pytorch resnet 101 模型参数数据 pytorch resnet 101 模型参数数据 pytorch resnet 101 模型参数数据 pytorch resnet 101 模型参数数据
keras_resnet_101_finetune.py例子
01-28
官方例子，深度学习专用，机器学习专用，代码简单，一看就会(keras resnet 101 finetune)
keras实现pspnet和resnet101-refinenet
爱CV
03-15 780
pspnet 留个坑 后续测试该网络模型；https://github.com/dhkim0225/keras-image-segmentation/blob/master/model/pspnet.py from keras.models import Model from keras.layers import Input from keras.layers.convolutional import Conv2D, Conv2DTranspose from keras.layers.pooling
resnet101预训练模型（PyTorch版本）
gitblog_09717的博客
10-19 1115
resnet101预训练模型（PyTorch版本） 【下载地址】resnet101预训练模型PyTorch版本 resnet101预训练模型（PyTorch版本） 项目地址: https://gitcode.com/open-so...
使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master
大彤小忆的博客
01-23 7353
  使用VGG16作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master的详细步骤→Windows10+Faster-RCNN-TensorFlow-Python3-master+VOC2007数据集。   如果使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master，在之前使用VGG16作为预训练模型的训练步骤基础上需要修改几个地方。 第一个，在之前的第6步时，改为下载预训练模型ResNet101，在./da
Keras预训练模型ResNet50权重文件配置指南
从给定的文件信息中，我们可以提取出以下知识点： ### 标题知识点 标题为 "resnet50_weights_tf_dim_...- Keras作为一个高级神经网络API，可以便捷地使用这些预训练模型和权重进行模型部署或进行进一步的训练和开发。
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值