Can I output the optimized model?

Question

Can I output the optimized model?

janhuang6 opened this issue 7 years ago · 6 comments

Once NoScope optimized the model for a video, can it output the optimized model so I can use it to process more videos from the same fixed camera without having to optimize again for each video? For instance, I have 5 videos from the same camera. NoScope found the optimized model from the 1st video, then how to run that model for the remaining 4 videos without the optimization again? Thank you!

Answer 1 · 2018-03-24T07:58:24.000Z

This is possible, take a look at https://github.com/stanford-futuredata/noscope/blob/master/exp/shuffled_small_cnn.py

Answer 2 · 2018-04-26T17:58:43.000Z

Hi, Daniel, thanks for directing me to the file shuffled_small_cnn.py. I made some change to this file. But when I ran NoScope, I found this file (and my changes too) were not executed. So what to do to execute it? Thanks! Jan

Answer 3 · 2018-04-30T21:42:27.000Z

Hi, Daniel, finally I run shuffled_small_cnn.py directly and it generated the Model output:
model_convnet_128_32_0.csv
model_convnet_128_32_0.h5
....
model_convnet_summary.csv

Now, is there a sample code that will read the model in and create the TensorFlow instance from it?

Thank you so much!
Jan

Answer 4 · 2018-04-30T23:28:42.000Z

I believe that's https://github.com/stanford-futuredata/noscope/blob/master/scripts/export-tf-graphs.py.

Answer 5 · 2018-05-02T00:52:05.000Z

Hi, sxhexe, thanks for the link. I executed that file "export-tf-graphs.py". It generated some .pb files. I think those are the TensorFlow Model Files. Is there a sample code that will read in the model .pb files and restore the TF model and run it?

Answer 6 · 2018-05-02T01:44:03.000Z

I don't know. Maybe look into tensorflow documentation?