In our latest release, version 220.127.116.11, we showcase several new loss samples that demonstrate binary classification, multi-class classification, multi-label classification and regression with the new MSE and MAE layers – all using the latest NVIDIA CUDA 11.7.1 / cuDNN 8.4.1 release.
The binary classification sample solves a simple 2-class classification problem, where the model learns to determine whether a given point falls within one of two circles of dots.
For more on this sample, see the Binary Classification Loss sample on GitHub.
The multi-classification sample solves a simple 3-class classification problem where the model learns to determine whether a given point falls within one of three blobs of dots.
For more on this sample, see the Multi-class Classification Loss sample on GitHub.
The multi-label classification sample solves problems where the model learns one or more labels per input. In this sample, the model learns one or more of 7 characteristics describing each handwritten character in the MNIST dataset.
For more on this sample, see the Multi-label Classification Loss sample on GitHub.
Regression problems train models to find certain values. MyCaffe solves regression problems using Mean Squared Error (MSE) or Mean Absolute Error (MAE).
The Mean Error Loss layer is used to solve regression problems with the type set to MSE for Mean Squared Error, or MAE for Mean Absolute Error.
For more on this sample, see the Mean Error Loss Sample on GitHub.
The following new features have been added to this release.
- CUDA 18.104.22.1686/cuDNN 22.214.171.124/nvapi 510/driver 516.40/516.59
- Windows 11 21H2
- Windows 10 21H2, OS Build 19044.1865, SDK 10.0.19041.0
- Added HINGE_LOSS layer support.
- Added MEAN_ERROR_LOSS layer support.
- Added support for dataset label recommendation.
- Improved object detection dataset building.
- Improved overall processing throughput when using multi-threaded operations.
- Upgraded to GoogleProtobuf 3.21.4.
The following bug fixes have been added to this release.
- Fixed bug in Impact Map.
- Fixed bug in MAELossLayer where normalization was incorrect.
- Fixed bug in Solver where ‘display’ was not being used.
For other great examples, including using Single Shot Multi-Box to detect gas leaks, or using Neural Style Transfer to create innovative and unique art, or creating Shakespeare sonnets with a CharNet, or beating PONG with Reinforcement Learning, check out the Examples page.
Happy Deep Learning with MyCaffe!