Skip to content

Releases: cvjena/cn24

CN24 2.0.5

20 Apr 21:21
Compare
Choose a tag to compare

Changes:

  • Switch to git-flow
  • Preliminary support for jpg/png streaming

CN24 v2.0.4

14 Apr 17:16
Compare
Choose a tag to compare

Changes:

  • Introduced CTest suite to catch errors

CN24 v2.0.3

12 Mar 12:41
Compare
Choose a tag to compare

Changes:

  • Fixed memory corruption issue with AdvancedMaxPoolingLayer and non-square pooling regions

CN24 v2.0.2

16 Jan 12:47
Compare
Choose a tag to compare

Changes:

  • Fixed missing layer time measurement facilities
  • classifyImage: Fixed missing spatial prior

CN24 v2.0.1

22 Dec 19:15
Compare
Choose a tag to compare

Changes:

  • Reduced number of compiler warnings significantly
  • runBenchmark: Added random content to data for benchmarks and gradient check

CN24 v2.0.0

13 Dec 17:52
Compare
Choose a tag to compare

Changes:

  • Several bug fixes
  • Introducing a compressed TensorStream format
  • Improved GraphViz network structure output
  • Better OpenCL and clBLAS support on Windows
  • Complete statistics overhaul improving data analysis significantly
    • Modular architecture allowing any component to report data
    • Added a "set experiment name" command to trainNetwork
    • Improved scripts for experiments
  • New layer InputDownSamplingLayer
  • New tool tensorStreamStats: Reads a TensorStream and displays information on sample distribution between classes
  • New tool makeCompressedTensorStream: New variant of makeTensorStream that uses compressed TensorStream format
  • New tool compressTensorStream: Compresses an existing TensorStream
  • New tool runBenchmark: Runs a repeatable benchmark for performance assessment

CN24 v1.3.2

06 Oct 10:29
Compare
Choose a tag to compare

Changes:

  • Fixed a bug that prevented loss sampling from working on OpenCL platforms

CN24 v1.3.1

28 Sep 14:22
Compare
Choose a tag to compare

Changes:

  • Improved startup times by memory mapping the dataset on supported systems (Linux,OS X)

CN24 v1.3.0

18 Sep 13:23
Compare
Choose a tag to compare

Changes:

  • Added QuickProp optimization algorithm
  • New advanced max-pooling layer
  • Performance improvements
  • Network is now represented as a graph for increased flexibility
  • Debug messages are now suppressed by default
  • Several bug fixes
  • trainNetwork: New command to output network structure as GraphViz file
  • trainNetwork: New command
  • TensorMath: OpenCL code path now uses clBLAS
  • ConvolutionLayer: Now supports stride, padding and grouping

CN24 v1.2.2

23 Jun 10:17
Compare
Choose a tag to compare

Changes:

  • Init: Fixed wrong delete operator, restricted OpenCL context to device
  • Init: Fixed conditional includes