Does TensorFlow.js support Node.js?
Can I import a TensorFlow or Keras model into the browser?
Can I export my model from the browser?
Since Version 0.11.1, you can export the topology and weights of
tf.Models to, or load them back
from, browser Local Storage and IndexedDB. You can also trigger downloading of
files or load
tf.Models from user-selected files in the browser. In addition,
tf.Models can be
sent to HTTP servers through
multipart/form-data requests. See the
tutorial page for more details.
We are currently working on these additional features for model import/export:
- Exporting and importing models in Node.js
tf.FrozenModels (i.e., models converted from TensorFlow
How does this relate to TensorFlow?
TensorFlow.js has an API similar to the TensorFlow Python API, however it does not support all of the functionality of the TensorFlow Python API. We are working hard to achieve API parity where it makes sense but also strive to provide an idiomatic JS API.
How does TensorFlow.js performance compare to the Python version?
In our experience, for inference, TensorFlow.js with WebGL is 1.5-2x slower than TensorFlow Python with AVX. For training, we have seen small models train faster in the browser and large models train up to 10-15x slower in the browser, compared to TensorFlow Python with AVX.
Please take a look at this benchmark to get more detailed performance measurements.
What is the difference between TensorFlow.js and deeplearn.js?
I still have some questions
Please feel free to look at our issues tracker and file a bug there. We also have a community mailing list for people to ask questions, get technical help, and share what they are doing with TensorFlow.js! To keep up to date with TensorFlow.js news follow us on twitter or join the announcement only mailing list.