MyCaffe 0.10.1.21-beta1

CUDA 10.1.105, cuDNN 7.5, nvapi 410, Native Caffe up to 10/24/2018, Windows 10-1809, Driver 419.17

MyCaffe now supports Neural Style Transfer using CUDA 10.1/cuDNN 7.5 to implement "A Neural Algorithm of Artistic Style" described by [1] using the VGG model [2], inspired by [3], which uses Caffe [4].

IMPORTANT NOTE: When using TCC mode, we recommend that ALL headless GPU’s are placed in TCC mode for we have experienced stability issues when using a mix of TCC and WDM modes with headless GPU’s.

REQUIRED SOFTWARE: 1.) Install NVIDIA CUDA 10.1 which you can download from https://developer.nvidia.com/cuda-downloads 2.) Install NVIDIA cuDNN 7.5 which you can download from https://developer.nvidia.com/cudnn 3.) Download and install Microsoft SQL Express 2016 (or later).

This release of the MyCaffe AI Platform and Test Applications has the following new additions: • CUDA 10.1.105/cuDNN 7.5 supported (with driver 419.17).

The following bug fixes are in this release: • Fixed bugs in Test Application user-interface. • Fixed bugs related to load-storage bug when using groups > 1. • Fixed bugs related to lower WDM accuracy than TCC for ResNet50. • Fixed bugs related to watch-dog-timeout with Blob minmax on large datasets.

To read more about cuDNN Neural Style Transfer in MyCaffe, see the SignalPop Blog.

Easily create the CIFAR-10 and MNIST datasets using the MyCaffe Test Application which you can download from the MyCaffe GitHub site.

Create and train the Neural Style Transfer, Recurrent Learning, Policy Gradient Reinforcement Learning, Auto-Encoder, DANN and ResNet models by following step-by-step instructions in the SignalPop Tutorials. And, to see other cool examples that show what MyCaffe can do, see the SignalPop Examples.

If you would like to visually design, develop, test and debug your models, see the SignalPop AI Designer specifically designed to enhance your MyCaffe deep learning.

Also, check out the SignalPop Universal Miner that not only gives you detailed information on each of your GPU's (such as temperature, fan speed, overclock, and usage), but allows you to easily mine Ethereum. When not training AI, put those GPU's to use making some Ether - never let a good GPU go to waste!

Happy ‘deep’ learning!

[1] L. Gatys, A. Ecker, M. Bethge [A Neural Algorithm of Artistic Style] (https://arxiv.org/abs/1508.06576), 2015, arXiv:1508:06576

[2] K. Simonyan, A. Zisserman Very Deep Convolutional Networks for Large-Scale Image Recognition arXiv:1409.1556

[3] ftokarev ftokarev/caffe Github, 2017, Github

[4] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama and T. Darrell, Caffe: Convolutional Architecture for Fast Feature Embedding, June 20, 2014.