[ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|

[ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Chiyuan Zhang
Hi all,

Mocha.jl is a Deep Learning framework for Julia, inspired by the C++ Deep Learning framework Caffe.

Please checkout the new IJulia Notebook demo of using pre-trained CNN on imagenet to do image classification: http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb

Here are detailed change log since the last release:

v0.0.3 2014.11.27

  • Interface
    • IJulia-notebook example
    • Image classifier wrapper
  • Network
    • Data transformers for data layers
    • Argmax, Crop, Reshape, HDF5 Output, Weighted Softmax-loss Layers
  • Infrastructure
    • Unit tests are extended to cover all layers in both Float32 and Float64
    • Compatibility with Julia v0.3.3 and v0.4 nightly build
  • Documentation
    • Complete User's Guide
    • Tutorial on image classification with pre-trained imagenet model

Best,
pluskid

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: [ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Alex Mikhalev
Good work!

On Friday, 28 November 2014 15:38:24 UTC, Chiyuan Zhang wrote:
Hi all,

<a href="https://github.com/pluskid/Mocha.jl" target="_blank" onmousedown="this.href='https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig';return true;" onclick="this.href='https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig';return true;">Mocha.jl is a Deep Learning framework for <a href="http://julialang.org/" target="_blank" onmousedown="this.href='http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw';return true;" onclick="this.href='http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw';return true;">Julia, inspired by the C++ Deep Learning framework <a href="http://caffe.berkeleyvision.org/" target="_blank" onmousedown="this.href='http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ';return true;" onclick="this.href='http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ';return true;">Caffe.

Please checkout the new IJulia Notebook demo of using pre-trained CNN on imagenet to do image classification: <a href="http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb" target="_blank" onmousedown="this.href='http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w';return true;" onclick="this.href='http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w';return true;">http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb

Here are detailed change log since the last release:

v0.0.3 2014.11.27

  • Interface
    • IJulia-notebook example
    • Image classifier wrapper
  • Network
    • Data transformers for data layers
    • Argmax, Crop, Reshape, HDF5 Output, Weighted Softmax-loss Layers
  • Infrastructure
    • Unit tests are extended to cover all layers in both Float32 and Float64
    • Compatibility with Julia v0.3.3 and v0.4 nightly build
  • Documentation
    • Complete User's Guide
    • Tutorial on image classification with pre-trained imagenet model

Best,
pluskid

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: [ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Ben Taylor
In reply to this post by Chiyuan Zhang
Great work Chiyuan. What is the best way to get in touch with you?

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: [ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Patrick Kofod Mogensen
In reply to this post by Chiyuan Zhang
Mocha.jl is such a great package, but wow the stars on github exploded in these past 14 days - is it this ANN or has there been some sort of course going on?

On Friday, November 28, 2014 at 10:38:24 AM UTC-5, Chiyuan Zhang wrote:
Hi all,

<a href="https://github.com/pluskid/Mocha.jl" target="_blank" rel="nofollow" onmousedown="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig&#39;;return true;" onclick="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig&#39;;return true;">Mocha.jl is a Deep Learning framework for <a href="http://julialang.org/" target="_blank" rel="nofollow" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw&#39;;return true;">Julia, inspired by the C++ Deep Learning framework <a href="http://caffe.berkeleyvision.org/" target="_blank" rel="nofollow" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ&#39;;return true;">Caffe.

Please checkout the new IJulia Notebook demo of using pre-trained CNN on imagenet to do image classification: <a href="http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb" target="_blank" rel="nofollow" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w&#39;;return true;">http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb

Here are detailed change log since the last release:

v0.0.3 2014.11.27

  • Interface
    • IJulia-notebook example
    • Image classifier wrapper
  • Network
    • Data transformers for data layers
    • Argmax, Crop, Reshape, HDF5 Output, Weighted Softmax-loss Layers
  • Infrastructure
    • Unit tests are extended to cover all layers in both Float32 and Float64
    • Compatibility with Julia v0.3.3 and v0.4 nightly build
  • Documentation
    • Complete User's Guide
    • Tutorial on image classification with pre-trained imagenet model

Best,
pluskid

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: [ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Stefan Karpinski
It was on the front page of Hacker News today.

On Tue, Sep 29, 2015 at 3:11 PM, Patrick Kofod Mogensen <[hidden email]> wrote:
Mocha.jl is such a great package, but wow the stars on github exploded in these past 14 days - is it this ANN or has there been some sort of course going on?


On Friday, November 28, 2014 at 10:38:24 AM UTC-5, Chiyuan Zhang wrote:
Hi all,

Mocha.jl is a Deep Learning framework for Julia, inspired by the C++ Deep Learning framework Caffe.

Please checkout the new IJulia Notebook demo of using pre-trained CNN on imagenet to do image classification: http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb

Here are detailed change log since the last release:

v0.0.3 2014.11.27

  • Interface
    • IJulia-notebook example
    • Image classifier wrapper
  • Network
    • Data transformers for data layers
    • Argmax, Crop, Reshape, HDF5 Output, Weighted Softmax-loss Layers
  • Infrastructure
    • Unit tests are extended to cover all layers in both Float32 and Float64
    • Compatibility with Julia v0.3.3 and v0.4 nightly build
  • Documentation
    • Complete User's Guide
    • Tutorial on image classification with pre-trained imagenet model

Best,
pluskid

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: [ANN] Mocha.jl v0.0.3, Image Classification IJulia Notebook Demo

Patrick Kofod Mogensen
That could probably be a major contributing factor!

On Tuesday, September 29, 2015 at 3:14:34 PM UTC-4, Stefan Karpinski wrote:
It was on the front page of Hacker News today.

On Tue, Sep 29, 2015 at 3:11 PM, Patrick Kofod Mogensen <<a href="javascript:" target="_blank" gdf-obfuscated-mailto="A0ZDjQ6YBgAJ" rel="nofollow" onmousedown="this.href=&#39;javascript:&#39;;return true;" onclick="this.href=&#39;javascript:&#39;;return true;">patrick....@...> wrote:
Mocha.jl is such a great package, but wow the stars on github exploded in these past 14 days - is it this ANN or has there been some sort of course going on?


On Friday, November 28, 2014 at 10:38:24 AM UTC-5, Chiyuan Zhang wrote:
Hi all,

<a href="https://github.com/pluskid/Mocha.jl" rel="nofollow" target="_blank" onmousedown="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig&#39;;return true;" onclick="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpluskid%2FMocha.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNGQMVS6gAxlNe7zoEPCFZaJwwsuig&#39;;return true;">Mocha.jl is a Deep Learning framework for <a href="http://julialang.org/" rel="nofollow" target="_blank" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fjulialang.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNFDhjHIhllRBZ-d-bLtw3PuY5T3Aw&#39;;return true;">Julia, inspired by the C++ Deep Learning framework <a href="http://caffe.berkeleyvision.org/" rel="nofollow" target="_blank" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fcaffe.berkeleyvision.org%2F\46sa\75D\46sntz\0751\46usg\75AFQjCNGBX9-k1FntcS_gdYLHjaHVnMs0bQ&#39;;return true;">Caffe.

Please checkout the new IJulia Notebook demo of using pre-trained CNN on imagenet to do image classification: <a href="http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb" rel="nofollow" target="_blank" onmousedown="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w&#39;;return true;" onclick="this.href=&#39;http://www.google.com/url?q\75http%3A%2F%2Fnbviewer.ipython.org%2Fgithub%2Fpluskid%2FMocha.jl%2Fblob%2Fmaster%2Fexamples%2Fijulia%2Filsvrc12%2Fimagenet-classifier.ipynb\46sa\75D\46sntz\0751\46usg\75AFQjCNGe_I8r46pE2pYVUjqloF1srkcH1w&#39;;return true;">http://nbviewer.ipython.org/github/pluskid/Mocha.jl/blob/master/examples/ijulia/ilsvrc12/imagenet-classifier.ipynb

Here are detailed change log since the last release:

v0.0.3 2014.11.27

  • Interface
    • IJulia-notebook example
    • Image classifier wrapper
  • Network
    • Data transformers for data layers
    • Argmax, Crop, Reshape, HDF5 Output, Weighted Softmax-loss Layers
  • Infrastructure
    • Unit tests are extended to cover all layers in both Float32 and Float64
    • Compatibility with Julia v0.3.3 and v0.4 nightly build
  • Documentation
    • Complete User's Guide
    • Tutorial on image classification with pre-trained imagenet model

Best,
pluskid

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to <a href="javascript:" target="_blank" gdf-obfuscated-mailto="A0ZDjQ6YBgAJ" rel="nofollow" onmousedown="this.href=&#39;javascript:&#39;;return true;" onclick="this.href=&#39;javascript:&#39;;return true;">julia-stats...@googlegroups.com.
For more options, visit <a href="https://groups.google.com/d/optout" target="_blank" rel="nofollow" onmousedown="this.href=&#39;https://groups.google.com/d/optout&#39;;return true;" onclick="this.href=&#39;https://groups.google.com/d/optout&#39;;return true;">https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.