简体   繁体   English

两个不同的深度学习框架如何使用同一模型?

[英]how can two different deep learning frameworks use the same model?

In the deep dream example using tensorflow here , the code references the inception5h model developed by google. 此处使用tensorflow的深梦示例中,代码引用了Google开发的inception5h模型。 However the original code from google here is using caffe, not tensorflow, probably because tensor flow did not exist then. 但是, 这里的 google原始代码使用的是caffe,而不是tensorflow,可能是因为当时不存在张量流。 How is it that the same model can be used by two different frameworks? 同一模型可以被两个不同的框架使用的情况如何? The 'deploy.prototxt' distributed with the bvlc_googlenet.caffemodel lists many convolution layers but the tensor flow implementation of the same model does not reference them and seems to use many fewer layers. 与bvlc_googlenet.caffemodel一起分发的'deploy.prototxt'列出了许多卷积层,但是同一模型的张量流实现未引用它们,并且似乎使用了更少的层。

If I get a pretained model without a 'deploy.prototxt' file, how can i determine how many layers the model has and how to reference them? 如果我得到一个没有'deploy.prototxt'文件的保留模型,我如何确定该模型有多少层以及如何引用它们?

If I get a pretrained model without a 'deploy.prototxt' file, how can i determine how many layers the model has 如果我得到的预训练模型没有'deploy.prototxt'文件,我如何确定模型有多少层

You can visualize your model, using draw_net.py script provided with caffe. 您可以使用caffe draw_net.py脚本来可视化模型。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM