Kevin Mader

I have the same error with Keras 2.1.3 and some ugly hacking seems to show that the generated weight names do not match up to the actual names of the...

the name issue can be fixed by renaming all of the layers (reloading weights) and then saving ``` base_model = load_model('variable_sized_model.h5') s_config = base_model.get_config() model_idx = np.random.choice(500) name_mapping = {v['name']:...

I have done a temporary workout around where you can change the config of the first layer (or any input layers, you have to rename layers as well with tensorflow...

My suspicion would be the model being evaluated from finish to start and isn't caching any of the intermediate results and recomputing every value every time (which would be `3*8*8*8`...

Wow, thanks I have never seen that crazy of a speed up between `-g` and `-03`, issue resolved! ``` Loading model Loading json ... done. elapsed time: 0.064939 s Running...

Running it on a vector sized `1, 1, 18000, 3` it seems to scale very differently (I guess the keras/tf runtime is mostly overhead while in frugally deep it is...

Well on the summary of the very poorly conducted benchmarks above, | Vector Size| Keras| Frugally Deep| |-----------:|-----:|------------:| | 600| 0.088| 0.990| | 18000| 0.493| 29.779| As the data gets...

Thanks, definitely seems to be a good approach. Unfortunately trying to figure out what tensorflow does with the model will probably be a lot messier. The caching would be the...

Yea that makes sense, I can try to figure out what tensorflow lite does as maybe there is something easy that works for this.

@Dobiasd sorry I started looking into it but got caught up by other projects, I'll try to dive a bit deeper next week and see if I can find anything