Tensorflow Hub Inception V3结构与Keras Inception V3结构相比? [英] Tensorflow Hub Inception V3 structure compared to Keras Inception V3 structure?

问题描述

我一直在使用Keras Inception V3.我相信Keras模型的结构如下图所示.但是，当我使用Tensorflow Hub中的Inception V3模型时，我认为(但不确定)，TF-Hub Inception V3模型包括直到IV3的Mixed7输出(第七个红色的"Concat")相反，Keras最多包含Mixed10输出(第10个红色的"Concat"框).有人可以确认吗? (或否认！)Tensorflow Hub Inception V3 Feature Vector模型的结构?有人可以告诉我在哪里可以找到显示TF-Hub模型的图像/图表的Tensorflow Hub文档吗?

I have been working Keras Inception V3. I believe the Keras model structure looks like the image below. But when I use the Inception V3 model from Tensorflow Hub, I think (but am not sure) that the TF-Hub Inception V3 model includes up until the Mixed7 output of IV3 (the 7th red "Concat" box), where Keras, in contrast, includes up to the Mixed10 output (10th red "Concat" box). Can someone confirm? (or deny!) the structure of the Tensorflow Hub Inception V3 Feature Vector model? Can someone tell me where to find Tensorflow Hub documentation showing images/diagrams of TF-Hub models to clarify?

推荐答案

Keras和SLIM之间的命名约定不同. https://tfhub.dev/google/imagenet/inception_v3/feature_vector/1是从SLIM代码创建的，并使用其命名约定以及数字和字母，请参见

The naming conventions differ between Keras and SLIM, unfortunately. https://tfhub.dev/google/imagenet/inception_v3/feature_vector/1 was created from SLIM code and uses its naming conventions with numbers and letters, see http://github.com/tensorflow/models/blob/master/research/slim/nets/ (or explore the Hub module on TensorBoard while training, if you are using it).

这篇关于Tensorflow Hub Inception V3结构与Keras Inception V3结构相比?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！