https://github.com/bloc97/convnetcl4j

OpenCL Accelerated Deep Learning for Java using Aparapi
https://github.com/bloc97/convnetcl4j

aparapi convolutional-neural-networks deep-learning deepcl gpu-accelerated-library neural-network open-cl

Last synced: about 1 year ago
JSON representation

OpenCL Accelerated Deep Learning for Java using Aparapi

• Host: GitHub
• URL: https://github.com/bloc97/convnetcl4j
• Owner: bloc97
• License: mit
• Created: 2017-10-03T22:37:49.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2019-09-10T23:47:56.000Z (over 6 years ago)
• Last Synced: 2025-01-25T13:31:07.371Z (over 1 year ago)
• Topics: aparapi, convolutional-neural-networks, deep-learning, deepcl, gpu-accelerated-library, neural-network, open-cl
• Language: Java
• Homepage:
• Size: 132 KB
• Stars: 1
• Watchers: 4
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# ConvNetCL4J

OpenCL Accelerated Deep Learning for Java using Aparapi

This is still WIP.  

#### Developement has stopped due to better alternatives such as:

 - Google Colab

 - Kaggle Kernels

Currently done:  

Convolutional Layer  

Transpose Convolution Layer  

ReLU Layer, LeakyReLU  

SGD  

SGD-Momentum  

MSE Loss  

Charbonnier Loss  

*High priority:*  

Add gradient checks and unit tests

Near future plans:  

Other Rectifiers (ELU, etc)  

Max Pooling Layer  

Fully Connected Layer  

Dilated Convolution Layer  

Adam