wassname/keras-js
1
0
Fork 0
mirror of https://github.com/wassname/keras-js.git synced 2026-09-13 12:41:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

add link to tensorflow playground

Browse Source
This commit is contained in:
Leon Chen
2016-10-25 10:58:45 -04:00
parent 02519af0b1
commit dcad54d47b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -2,7 +2,7 @@
Run [Keras](https://github.com/fchollet/keras) models (trained using Tensorflow backend) in your browser, with GPU support. Models are created directly from the Keras JSON-format configuration file, using weights serialized directly from the corresponding HDF5 file.
Inspiration is drawn from a number of deep learning / neural network libraries for JavaScript and the browser, including [ConvNetJS](https://github.com/karpathy/convnetjs), [synaptic](https://github.com/cazala/synaptic), [brain](https://github.com/harthur/brain), [CaffeJS](https://github.com/chaosmail/caffejs), [MXNetJS](https://github.com/dmlc/mxnet.js). However, the focus of this library is on inference only.
Inspiration is drawn from a number of deep learning / neural network libraries for JavaScript and the browser, including [Tensorflow Playground](http://playground.tensorflow.org/), [ConvNetJS](https://github.com/karpathy/convnetjs), [synaptic](https://github.com/cazala/synaptic), [brain](https://github.com/harthur/brain), [CaffeJS](https://github.com/chaosmail/caffejs), [MXNetJS](https://github.com/dmlc/mxnet.js). However, the focus of this library is on inference only.
Tensor operations are extended on top of the [ndarray](https://github.com/scijs/ndarray) library. GPU support is powered by WebGL through [weblas](https://github.com/waylonflinn/weblas).