Watch the screencast
This demo imports an MNIST ConvNet trained in Keras Python, then makes predictions with TensorFlow.js
- clone it, cd into it,
npm install && ng serve
tensorflowjs_converter --input_format keras keras/yourWeights.h5 src/assets
Episode 97 - TensorFlow.js Quick Start
Watch the screencast
This demo imports an MNIST ConvNet trained in Keras Python, then makes predictions with TensorFlow.js
npm install && ng serve
tensorflowjs_converter --input_format keras keras/yourWeights.h5 src/assets
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 :)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.