caffe训练分类完整流程

柔情只为你懂 2022-07-13 02:18 274阅读 0赞

[Caffe均值文件mean.binaryproto转mean.npy][Caffe_mean.binaryproto_mean.npy]

[深度学习（十三）caffe之训练数据格式][caffe]

[Caffe在Cifar10上复现ResNet][Caffe_Cifar10_ResNet]

[使用caffe训练自己的数据][caffe 1]

[使用caffe fine-tune一个单标签图像分类模型][caffe fine-tune]

[如何用caffe训练图像分类深度学习模型][caffe 2]

[Caffe下自个儿的数据训练和测试][Caffe]

[Deep Learning Resources][]

[caffe示例实现之5用CaffeNet训练与测试自己的数据集][caffe_5_CaffeNet]

[另一个caffe实例整个流程][caffe 3]

[使用caffe训练好的模型进行分类][caffe 4]

[用训练好的caffe模型进行分类完整版][caffe 5]

[为了caffe（七）做kaggle上的mnist][caffe_kaggle_mnist]

[\*\_train\_test.prototxt,\*\_deploy.prototxt,\*\_slover.prototxt文件编写时注意事项][train_test.prototxt_deploy.prototxt_slover.prototxt]

[Caffe学习系列(20)：用训练好的caffemodel来进行分类][Caffe_20_caffemodel]

[使用Caffe对图片进行训练并分类的简单流程][Caffe 1]

[caffe的python接口学习：用训练好的模型（caffemodel或者h5）来分类新的图片][caffe_python_caffemodel_h5]

[根据 \*\_train\_test.prototxt文件生成 \*\_deploy.prototxt文件][_train_test.prototxt_ _deploy.prototxt]

[深度学习-LeCun、Bengio和Hinton的联合综述（上）][-LeCun_Bengio_Hinton]

# [浅谈caffe中train\_val.prototxt和deploy.prototxt文件的区别][caffe_train_val.prototxt_deploy.prototxt]    #

[Caffe Prediction][]

[Caffe-使用C++的分类接口][Caffe-_C]

[caffe在画accuracy曲线图及对某文件夹下多张图片预测分类时的问题解决][caffe_accuracy]

https://github.com/shuokay/resnet/blob/master/resnet-small.py

https://github.com/machrisaa/tensorflow-vgg

https://github.com/vgenty/resnet18

https://github.com/KaimingHe/deep-residual-networks

https://www.zhihu.com/question/41990278

https://github.com/BVLC/caffe/wiki/Model-Zoo

https://zhuanlan.zhihu.com/p/24001523

[Caffe_mean.binaryproto_mean.npy]: http://blog.csdn.net/hyman_yx/article/details/51732656
[caffe]: http://blog.csdn.net/hjimce/article/details/49248231
[Caffe_Cifar10_ResNet]: http://blog.csdn.net/a_1937/article/details/51507545
[caffe 1]: http://blog.csdn.net/thy_2014/article/details/51614679
[caffe fine-tune]: http://blog.csdn.net/u010358677/article/details/53305333
[caffe 2]: https://zhuanlan.zhihu.com/p/24001523
[Caffe]: http://www.myexception.cn/internet/1975067.html
[Deep Learning Resources]: http://blog.csdn.net/qq_26898461/article/details/50887070
[caffe_5_CaffeNet]: http://blog.csdn.net/liumaolincycle/article/details/48475479
[caffe 3]: http://blog.csdn.net/wd1603926823/article/details/52763433
[caffe 4]: http://blog.csdn.net/thy_2014/article/details/51648730
[caffe 5]: http://blog.csdn.net/wangbo792450190/article/details/52583749
[caffe_kaggle_mnist]: http://blog.csdn.net/ddqqfree123/article/details/52389337
[train_test.prototxt_deploy.prototxt_slover.prototxt]: http://blog.csdn.net/sunshine_in_moon/article/details/49472901
[Caffe_20_caffemodel]: http://www.cnblogs.com/denny402/p/5111018.html
[Caffe 1]: http://blog.csdn.net/deeplearninglc007/article/details/40086503
[caffe_python_caffemodel_h5]: http://blog.csdn.net/u010417185/article/details/52150363
[_train_test.prototxt_ _deploy.prototxt]: http://blog.csdn.net/u010417185/article/details/52137825
[-LeCun_Bengio_Hinton]: http://www.csdn.net/article/2015-06-01/2824811
[caffe_train_val.prototxt_deploy.prototxt]: http://blog.csdn.net/fx409494616/article/details/53008971
[Caffe Prediction]: http://blog.csdn.net/ayst123/article/details/44223321
[Caffe-_C]: http://blog.csdn.net/fx409494616/article/details/53009159
[caffe_accuracy]: http://blog.csdn.net/wd1603926823/article/details/52625733