menoh: Haskell binding for Menoh DNN inference library
Menoh is a MKL-DNN based DNN inference library for ONNX models. See https://github.com/pfnet-research/menoh/ for details.
[Skip to Readme]
Flags
Manual Flags
| Name | Description | Default |
|---|---|---|
| buildexamples | build example programs | Enabled |
Use -f <flag> to enable a flag, or -f -<flag> to disable that flag. More info
Downloads
- menoh-0.3.0.tar.gz [browse] (Cabal source package)
- Package description (as included in the package)
Maintainer's Corner
For package maintainers and hackage trustees
Candidates
- No Candidates
| Versions [RSS] | 0.1.0, 0.1.1, 0.2.0, 0.3.0 |
|---|---|
| Dependencies | aeson (>=0.8 && <1.5), base (>=4.7 && <5), bytestring (>=0.10 && <0.11), containers (>=0.5 && <0.7), filepath (>=1.3 && <1.5), JuicyPixels (>=3.2.7 && <3.4), menoh, monad-control (>=1.0 && <1.1), optparse-applicative (>=0.11 && <0.15), transformers (>=0.3 && <0.6), vector (>=0.10 && <0.13) [details] |
| Tested with | ghc ==7.8.4, ghc ==7.10.3, ghc ==8.0.2, ghc ==8.2.2, ghc ==8.4.3 |
| License | MIT |
| Copyright | Copyright 2018 Preferred Networks, Inc. |
| Author | Masahiro Sakai <sakai@preferred.jp> |
| Maintainer | Masahiro Sakai <sakai@preferred.jp> |
| Category | Machine Learning, Deep Learning |
| Source repo | head: git clone https://github.com/pfnet-research/menoh-haskell/ |
| Uploaded | by MasahiroSakai at 2018-11-08T10:08:17Z |
| Distributions | |
| Executables | mnist_example, vgg16_example |
| Downloads | 2436 total (12 in the last 30 days) |
| Rating | (no votes yet) [estimated by Bayesian average] |
| Your Rating | |
| Status | Docs uploaded by user Build status unknown [no reports yet] |
Readme for menoh-0.3.0
[back to package description]menoh-haskell
Haskell binding for Menoh DNN inference library.
Requirements
Build
Execute below commands in root directory.
sh retrieve_data.sh
stack build
Running VGG16 example
Execute below command in root directory.
cd menoh
stack exec vgg16_example
Result is below
vgg16 example
fc6_out: -19.079105 -37.94045 -16.185831 25.51685 4.432623 ...
top 5 categories are:
8 0.958079 n01514859 hen
7 0.039541963 n01514668 cock
86 0.0018722217 n01807496 partridge
82 0.00027406064 n01797886 ruffed grouse, partridge, Bonasa umbellus
97 0.00003177848 n01847000 drake
Please give --help option for details
stack exec vgg16_example --help
Installation
stack install
Documents
-
API reference manual is available on Hackage.
-
see mnist_example.hs and vgg16_example.hs for example usage.
License
Note: retrieve_data.sh downloads data/VGG16.onnx. data/VGG16.onnx is generated by onnx-chainer from pre-trained model which is uploaded
at http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel
That pre-trained model is released under Creative Commons Attribution License.