VGG16 pre-trained model 实现image classification

　站在巨人的肩膀上！使用VGG预先训练好的weight来，进行自己的分类。

　下一阶段是在这上面进行自己的修改，完成自己想要的功能。

Github源码

Github上有我全部的工程代码。

环境配置

　　Python3.5
　　Keras2.0
　　TensorFlow
　　我这里是在Windows10, LINUX一样配置对应的package就好了，记得路径改了就ok

关于各种错误：

　　去github glist中有我的回答，几乎包括了所有可能发生的错误（我几乎碰到了所有可能的错误，囧）。

　　直接搜错误log 或 搜我的id : luntai就可以找到。

测试

n02123045 tabby, tabby cat

n02391049 zebra

　　一个模型搞了一整天，跪在坚持，贵在坚持。陪这种东西很虐心 但是孰能手巧。慢慢就会找到感觉了。

时间： 2024-10-31 04:48:04

VGG16 pre-trained model 实现image classification的相关文章

Transfer learning & The art of using Pre-trained Models in Deep Learning

原文网址:  https://www.analyticsvidhya.com/blog/2017/06/transfer-learning-the-art-of-fine-tuning-a-pre-trained-model/ Introduction Neural networks are a different breed of models compared to the supervised machine learning algorithms. Why do I say so? Th

『计算机视觉』Mask-RCNN_训练网络其三：model准备

一.模型初始化 1.创建模型并载入预训练参数 准备了数据集后,我们开始构建model,training网络结构上一节已经介绍完了,现在我们看一看训练时如何调用training结构的网络. 如上所示,我们首先建立图结构(详见上节『计算机视觉』Mask-RCNN_训练网络其二:train网络结构),然后选择初始化参数方案 例子(train_shape.ipynb)中使用的是COCO预训练模型,如果想要"Finds the last checkpoint file of the last traine

Convolution Fundamental II

Practical Advice Using Open-Source Implementation We have learned a lot of NNs and ConvNets architectures It turns out that a lot of these NN are difficult to replicated. because there are some detail that may not presented on its paper. There are so

models-caffes-大全

caffe的伯克利主页:http://caffe.berkeleyvision.org/caffe的github主页:https://github.com/BVLC/caffe caffe的models: http://dl.caffe.berkeleyvision.org/ Index of / ../ mit_mini_places/ 01-Mar-2016 12:18 - bvlc_alexnet.caffemodel 22-Aug-2014 04:36 243862414 bvlc_go

（转）ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks

ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks by KOUSTUBH this blog from: http://cv-tricks.com/cnn/understand-resnet-alexnet-vgg-inception/ Convolutional neural networks are fantastic for visual recogn

机器学习算法之旅（转载）

http://machinelearningmastery.com/a-tour-of-machine-learning-algorithms/ In this post, we take a tour of the most popular machine learning algorithms. It is useful to tour the main algorithms in the field to get a feeling of what methods are availabl

组会准备

LSTM Networks for Sentiment Analysis Summary This tutorial aims to provide an example of how a Recurrent Neural Network (RNN) using the Long Short Term Memory (LSTM) architecture can be implemented using Theano. In this tutorial, this model is used t

fastText一个库用于词表示的高效学习和句子分类

fastText fastText 是 Facebook 开发的一个用于高效学习单词呈现以及语句分类的开源库. 要求 fastText 使用 C++11 特性,因此需要一个对 C++11 支持良好的编译器,可以使用: (gcc-4.6.3 或者更新版本) 或者 (clang-3.3 或者更新版本) 我们使用 Makefile 进行编译,因此需要 make 工具.为了运行单词相似度演示脚本,我们需要如下工具: python 2.6 or newer numpy & scipy 构建 fastTex

（转） Deep Learning in a Nutshell: Core Concepts

Deep Learning in a Nutshell: Core Concepts Share: Posted on November 3, 2015by Tim Dettmers 7 CommentsTagged cuDNN, Deep Learning, Deep Neural Networks, Machine Learning,Neural Networks This post is the first in a series I’ll be writing for Parallel