MyCaffe 0.10.1.283-beta1

CUDA 10.1.243, cuDNN 7.6.4, nvapi 430, Native Caffe up to 10/24/2018, Windows 10-1903, Driver 430.86

MyCaffe[1] (a complete C# re-write of CAFFE[2]) now supports Deep Q-Learning[3][4] with a NoisyNet[5] and Prioritized Replay Buffer[6], all supported by the new DQN trainer and do so with the newly released CUDA 10.1.243, CuDNN 7.6.4 and the dual RNN/RL training that allows multi-pass training where the first pass involves RNN training and the second pass involves RL training that uses the already trained RNN side of the model.

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 10.1.243 which you can download from https://developer.nvidia.com/cuda-downloads 2.) Install NVIDIA cuDNN 7.6.4 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 10.1.243/cuDNN 7.6.4 supported (with driver 430.86 or above). • Windows 1903, OS Build 18362.449 now supported. • Added new DetectionEvaluate Layer for SSD. • Added new DetectionOutput Layer for SSD. • Added new dynamic layer creation support. • Added new VideoData Layer for SSD. • Added new MyCaffe.model ModelBuilder for programmatic model construction. • Added new dataset loading support for the VOC0712 dataset. • Added new TarFile extraction support to MyCaffe.basecode. • Added new Label query hit percentages and Label epoch information to OnTrainingIteration • Removed Masking out columns from Image Database.

The following bug fixes are in this release: • Fixed bugs related to opening a new source ID when already open with another - fixes MNIST and CIFAR-10 dataset creation. • Fixed bugs related to missing model and solver files for c51 and noisy.dqn models. • Fixed bugs in AnnotatedDataLayer related to using the random seed. • Fixed bugs in BBoxUtility related to ComputeConfLoss with match. • Fixed bugs in DetectionEvaluation Layer forward pass. • Fixed bugs in Data Transformer when applied to the Run Net (caused inaccuracies in the deploy/run models).

Easily run Neural Style, train Deep Q-Learning[3][4] or Policy Gradient[1] models to beat Pong or Cart-Pole, or 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 Deep Q-Learning[3][4], Policy Gradient[1], 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 keeps your GPU's cool as you train, but also gives you detailed information on each of your GPU's (such as temperature, fan speed, overclock, and usage), and 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] MyCaffe: A Complete C# Re-Write of Caffe with Reinforcement Learning by D. Brown, 2018.

[2] Caffe: Convolutional Architecture for Fast Feature Embedding by Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell, 2014, arXiv:1408.5093

[3] GitHub: Google/dopamine licensed under the Apache 2.0 License;

[4] Dopamine: A Research Framework for Deep Reinforcement Learning by Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar, Marc G. Bellemare, 2018, arXiv:1812.06110

[5] Noisy Networks for Exploration by Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg, 2018, arXiv:1706.10295

[6] Prioritized Experience Replay by Tom Schaul, John Quan, Ioannis Antonoglou, David Silver, 2016, arXiv:1511.05952