7

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?

Milind Deore
  • 2,887
  • 5
  • 25
  • 40
Subhash_Reddy
  • 438
  • 6
  • 13

1 Answers1

6

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 :)

Andrew Harp
  • 331
  • 1
  • 4
  • I [retrained](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py) and [optimized for inception](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/optimize_for_inference.py) the inception V3. The retrained APK works with inference time 1200~2000ms and with inception5H model, the APK works at 200~400ms. Is it possible to attain similar inference time on my retrained APK, with inceptionV3? – Subhash_Reddy Apr 22 '17 at 00:46
  • Andrew Harp thanks for the information about InceptionV5. I have tried retraining/finetune the [inceptionV1](https://github.com/tensorflow/models/blob/master/slim/scripts/finetune_inception_v1_on_flowers.sh) slim model and am facing [this issue](http://stackoverflow.com/questions/43647446/no-operation-named-input-in-the-graph-error-while-fine-tuning-retraining-ince) please help me out. – Subhash_Reddy Apr 27 '17 at 03:59