DeepLearn.js 0.3.0 release, add support for iOS
DeepLearn.js 0.3.0 has been released, this is a hardware-accelerated machine learning JavaScript library that can run entirely in the browser without installation and back-end processing, open source by Google.
The major updates for this release include:
- Added support for iOS
- Added optimizer (Adam, AdaGrad, AdaDelta, RMSProp)
- New
math.cos
,math.tan
,math.asin
,math.acos
,math.atan
,math.sinh
,math.cosh
,math.abs
- New
math.oneHot
andmath.multinomial
#160 - Added
NDArray.getValuesAsync()
to download values #146 from the GPU asynchronously - Added
math.concat[1-4]D
and addedmath.slice[1-4]D
- Fix
NDArray.randTruncatedNormal
Bug #172 - Added when the glsl fragment shader can not compile when highlighted
- Faster ops restore (min / max / reduce_sum / logsumexp) #145
- Faster matrix multiplication and convolution/pool #129
- Added script for model builder training data preprocessing #136
- Reference measurement improvement #140
For more information, please refer to the release notes