Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

Inception5h vs Inception V4, what is 5h

I have been following github repository for "Tensorflow on Android".

This link, shows all the inception models but not inception5h. The demo application for tensorflow on github uses inception5h, as shown here

   new_http_archive(
      name = "inception5h",
      build_file = "models.BUILD",
      url = "https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip",
      sha256 = "d13569f6a98159de37e92e9c8ec4dae8f674fbf475f69fe6199b514f756d4364"
    )

Please explain

1.Why it is inception5h and not inceptionV5?

2.Why is inception5h not listed in the models link above?

like image 395
Subhash_Reddy Avatar asked Apr 18 '17 04:04

Subhash_Reddy


People also ask

What is inception-v4?

Inception-v4 is a convolutional neural network architecture that builds on previous iterations of the Inception family by simplifying the architecture and using more inception modules than Inception-v3. Source: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.

Is inception-v4 better than Inception-v3?

Inception-v4, evolved from GoogLeNet / Inception-v1, has a more uniform simplified architecture and more inception modules than Inception-v3. From the below figure, we can see the top-1 accuracy from v1 to v4. And Inception-v4 is better than ResNet.

What is the difference between inception V2 and Inception-v3?

Inception V3 is similar to and contains all the features of Inception V2 with following changes/additions: Use of RMSprop optimizer. Batch Normalization in the fully connected layer of Auxiliary classifier. Use of 7×7 factorized Convolution.

What is inception net?

Inception Network. An inception network is a deep neural network with an architectural design that consists of repeating components referred to as Inception modules. As mentioned earlier, this article focuses on the technical details of the inception module.


1 Answers

Inception 5h is equivalent to Inception V1. This just comes down to a bit of confusion of what versioning scheme we were publishing things under :)

like image 137
Andrew Harp Avatar answered Sep 24 '22 19:09

Andrew Harp