Mocha.jl v0.0.5

[pluskid]

Mocha.jl v0.0.5

v0.0.5 2014.12.20

• Infrastructure
  • {Breaking Changes} cuDNN 6.5 R2 (Release Candidate) (@JobJob)
    • cuDNN 6.5 R2 is NOT backward compatible with 6.5 R1
    • Forward convolution speed up
    • Pooling with padding is supported
    • Mac OS X is supported
  • 4D-tensor -> ND-tensor
    • Mocha is now capable of handling general ND-tensor
    • Except that (for now) ConvolutionLayer and PoolingLayer still requires the inputs to be 4D
    • The generalization is almost backward compatible, except
      • The interface for ReshapeLayer changed b/c the target shape needs to be ND, instead of 4D now
      • Parameters added for some layers to allow the user to specify which dimension to operate on
      • The output of InnerProductLayer is now 2D-tensor instead of 4D
    • Unit-tests are expanded to cover test cases for ND-tensor when applicable
• Interface
  • print a constructed Net to get a brief overview of the geometry of input/output blobs in each layers
• Documentation
  • Setup the Roadmap Ticket, duscussions/suggestions are welcome
  • Update everything to reflect 4D -> ND tensor changes
  • Document for parameter norm constraints
  • Developer's Guide for blob and layer API

[lindahua]

@ViralBShah I think you may add @pluskid as a packager. His recent contributions have been great.

[ViralBShah]

Great idea. Done. @pluskid You should have received an invitation. You should be able to merge PRs to METADATA by yourself now.

[pluskid]

@ViralBShah @lindahua Wow, that's awesome! Thank you very much! :)