MyCaffe 0.10.2.124-beta1

A complete C# re-write of Berkeley's open source Convolutional Architecture for Fast Feature Encoding (CAFFE) for Windows C# Developers with full On-line Help, now with SiameseNet, NoisyNet, Deep Q-Network and Policy Gradient Reinforcement Learning, cuDNN LSTM Recurrent Learning, and Neural Style Transfer support!

This is a prerelease version of MyCaffe.
Install-Package MyCaffe -Version 0.10.2.124-beta1
dotnet add package MyCaffe --version 0.10.2.124-beta1
<PackageReference Include="MyCaffe" Version="0.10.2.124-beta1" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add MyCaffe --version 0.10.2.124-beta1
The NuGet Team does not provide support for this client. Please contact its maintainers for support.

MyCaffe AI Platform and Test Application (CUDA 10.2.89, cuDNN 7.6.5) with Siamese Net KNN, One-Shot Learning and Python Support
CUDA 10.2.89, cuDNN 7.6.5, nvapi 435, Native Caffe up to 10/24/2018, Windows 10-1903, Driver 441.66 and 441.87

MyCaffe[1] (a complete C# re-write of CAFFE[2]) now supports the Siamese Net[3][4] with KNN and Contrastive Loss and does so with the newly released CUDA 10.2.89, CuDNN 7.6.5 for easy One-Shot learning with both C# and Python support!

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 10.2.89 which you can download from https://developer.nvidia.com/cuda-downloads
2.) Install NVIDIA cuDNN 7.6.5 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 10.2.89/cuDNN 7.6.5 supported (with driver 441.66 or above).
  • Windows 1903, OS Build 18363.449 now supported.
  • Added new XML Documentation files for intellisense.
  • Added improved Python programmability.
  • Added new KNN support to Decode Layer for Siamese Nets.
  • Added new Centroid learning focus to ContrastiveLoss layer.
  • Added new MyCaffeImageDatabase2 with QueryState and improved background loading.
  • Added new image diagnostic output support to Data Layer for debugging.
  • Added new noisy data for secondary image in Data Layer when used with Siamese Nets.
  • Added new optional image masking to Data Layer.
  • Added new optional label mapping to Data Layer.
  • Added sub with a subset support.
  • Added boost query hit percent support.
  • Added CudaDnn.copy support to copy from one of two sourced based on similarity.
  • Added CudaDnn.channel_fill support.
  • Added CudaDnn.channel_compare support.
  • Added CudaDnn.fill support.

The following bug fixes are in this release:

  • Fixed bugs in Image Database related to super boost probability and label balancing.
  • Fixed bugs in Image Database related to querying boosted images when none exist.
  • Fixed bugs in help related to LaTex function generation.
  • Fixed bugs related to low-level handle management.
  • Fixed bugs related to thread synchronization on dispose.
  • Fixed bugs related to Decode parameters not persisting.
  • Optimized DataTransfer Transform methods for both float and double.
  • Optimized SimpleDatum support for both float and double without conversion.

Easily run Siamese Nets[3][4], Neural Style, train Deep Q-Learning 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 Siamese Net[3][4], Deep Q-Learning with NoisyNet and Experienced Replay, 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] Siamese Network Training with Caffe by Berkeley Artificial Intelligence (BAIR)

[4] Siamese Neural Network for One-shot Image Recognition by G. Koch, R. Zemel and R. Salakhutdinov, ICML 2015 Deep Learning Workshop, 2015.

MyCaffe AI Platform and Test Application (CUDA 10.2.89, cuDNN 7.6.5) with Siamese Net KNN, One-Shot Learning and Python Support
CUDA 10.2.89, cuDNN 7.6.5, nvapi 435, Native Caffe up to 10/24/2018, Windows 10-1903, Driver 441.66 and 441.87

MyCaffe[1] (a complete C# re-write of CAFFE[2]) now supports the Siamese Net[3][4] with KNN and Contrastive Loss and does so with the newly released CUDA 10.2.89, CuDNN 7.6.5 for easy One-Shot learning with both C# and Python support!

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 10.2.89 which you can download from https://developer.nvidia.com/cuda-downloads
2.) Install NVIDIA cuDNN 7.6.5 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 10.2.89/cuDNN 7.6.5 supported (with driver 441.66 or above).
  • Windows 1903, OS Build 18363.449 now supported.
  • Added new XML Documentation files for intellisense.
  • Added improved Python programmability.
  • Added new KNN support to Decode Layer for Siamese Nets.
  • Added new Centroid learning focus to ContrastiveLoss layer.
  • Added new MyCaffeImageDatabase2 with QueryState and improved background loading.
  • Added new image diagnostic output support to Data Layer for debugging.
  • Added new noisy data for secondary image in Data Layer when used with Siamese Nets.
  • Added new optional image masking to Data Layer.
  • Added new optional label mapping to Data Layer.
  • Added sub with a subset support.
  • Added boost query hit percent support.
  • Added CudaDnn.copy support to copy from one of two sourced based on similarity.
  • Added CudaDnn.channel_fill support.
  • Added CudaDnn.channel_compare support.
  • Added CudaDnn.fill support.

The following bug fixes are in this release:

  • Fixed bugs in Image Database related to super boost probability and label balancing.
  • Fixed bugs in Image Database related to querying boosted images when none exist.
  • Fixed bugs in help related to LaTex function generation.
  • Fixed bugs related to low-level handle management.
  • Fixed bugs related to thread synchronization on dispose.
  • Fixed bugs related to Decode parameters not persisting.
  • Optimized DataTransfer Transform methods for both float and double.
  • Optimized SimpleDatum support for both float and double without conversion.

Easily run Siamese Nets[3][4], Neural Style, train Deep Q-Learning 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 Siamese Net[3][4], Deep Q-Learning with NoisyNet and Experienced Replay, 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] Siamese Network Training with Caffe by Berkeley Artificial Intelligence (BAIR)

[4] Siamese Neural Network for One-shot Image Recognition by G. Koch, R. Zemel and R. Salakhutdinov, ICML 2015 Deep Learning Workshop, 2015.

Release Notes

MyCaffe AI Platform

This package is not used by any popular GitHub repositories.

Version History

Version Downloads Last updated
0.10.2.124-beta1 34 1/21/2020
0.10.2.38-beta1 58 11/29/2019
0.10.1.283-beta1 67 10/28/2019
0.10.1.221-beta1 73 9/17/2019
0.10.1.169-beta1 200 7/8/2019
0.10.1.145-beta1 201 5/31/2019
0.10.1.48-beta1 215 4/18/2019
0.10.1.21-beta1 209 3/5/2019
0.10.0.190-beta1 287 1/15/2019
0.10.0.140-beta1 229 11/29/2018
0.10.0.122-beta1 251 11/15/2018
0.10.0.75-beta1 254 10/7/2018