I tried to do the example from scratch, but on the line:

this.model = await tf.loadModel('/assets/model.json');

I'm getting this error:

SyntaxError: Unexpected token < in JSON at position 0

In my assets folder I just copy/pasted the same assets that this repo:

assets
├── group1-shard1of1
├── group2-shard1of1
├── group3-shard1of2
├── group3-shard2of2
├── group4-shard1of1
└── model.json

And the file that contains the line:

this.model = await tf.loadModel('/assets/model.json');

is in the same level than assets.

Any idea about why is happening this? I would like to load the model 😄

Thanks!

Hi, I'm looking for a way to make tensorflow(js) models as portable as possible.

The only problem i have at the moment is that the bar chart showing the results of the tfjs model does not seem to be working. The linear model output is showing fine, but the bar chart is not.
It works fine in ng serve but building the webapp with and without "--prod" does not. href is pointing at "dist/assets".

Is there any way to make such apps completely local? because even the official tensorflowjs examples (those that work) need something like npm to create a server.

Thanks for the help :)