Deep Learning/Installing Pylearn2 on CUDA
[
Front page
] [
New
|
List of pages
|
Search
|
Recent changes
]
Start:
[[labs.beatcraft.com]]~
[[Deep Learning]]~
#Contents
*Overview [#u3eb53fe]
>
This article explains how to install [[Pylearn2>http://de...
Since most of functionality of Pylearn2 is built upon the...
in Pylearn2 are expressed in mathematical expressions. Th...
~
This article uses the same hardware, which is used for ex...
The system is equipped with Tesla K20c, and CUDA tools 6....
*Setting up Pylearn2 [#i37fce6c]
** Installing Ubuntu 14.04 and Configuring CUDA [#x720f1ec]
>
To enable Pylearn2 to work on GPU at backend correctly, y...
Please check this article for installing CUDA Toolkit 6.5...
*** Python Modules [#l95b7946]
>
If the Python modules, which are required for installing ...
please use the command line ''apt-get install''. Otherwis...
** Installing Theano [#e404e72c]
>
First, the required libraries, which are needed for insta...
The [[list of requirements>http://deeplearning.net/softwa...
~
- Python 2.6 or greater (This is the default Python on Ub...
- g++
- python-dev
- Numpy 1.5.0 or greater
- SciPy
- BLAS (Basic Liner Algebra Subprograms, Level3 function ...
~
Then, the following optional packages are also installed.~
~
- node
- Sphinx 0.5.1 or greater
- Git
- pydot
- CUDA (already installed)
- libgpuarray
>
For the reference, please read the article listed below. ...
[[Easy Installation of an Optimized Theano on Current Ubu...
>
Install git and Python modules by applying apt-get.~
$ sudo apt-get install git python-dev paython-numpy pyth...
>
To install BLAS, use OpenBLAS. The instructions of how to...
Please follow the instructions. (The package of OpenBLAS ...
Therefore, please build and install OpenBLAS from the scr...
$ sudo apt-get install gfortran
$ git clone git://github.com/xianyi/OpenBLAS
$ cd OpenBLAS
$ make FC=gfortran
$ sudo make PREFIX = /usr/local install
$ sudo idconfig
>
Before installing libgpuarray, please install the require...
please visit [[this page>http://deeplearning.net/software...
$ sudo apt-get install cmake check python-mako cython
>
Obtaining the source code of libbgpuarray from git.
$ git clone https://github.com/Theano/libgpuarray.git
$ cd libgpuarray
>
If you try to execute the build command of Cmake, an erro...
To avoid this error to happen, CMakeLists.text will be mo...
$ cd src
$ vim CMakeLists.text
~
Before modifying the CMakeLists.text
if(CUDA_FOUND)
target_link_libraries(pthread $ {CUDADRV_LIBRARY} $ {CUD...
target_link_libraries(gpuarray-static $ {CUDADRV_LIBRARY...
endif()
　↓
After modifying the CMakeLists.text
if(CUDA_FOUND)
target_link_libraries(gpuarrat pthread $ {CUDADRV_LIBRAR...
target_link_libraries(gpuarray-static pthread $ {CUDADRV...
endif()
>
After the modification is completed, going back to the di...
$ cd ..
$ mkdir Build
$ cd Build
$ cmake.. -DCMAKE_BUILD_TYPE=Release
$ make
$ sudo make install
$ sudo idconfig
$ cd ..
>
pygpu, which is included in libgpuarray, is installed by ...
$ python setup.py build
$ sudo python setup.py install
>
This is basically the end of installing the pre-requireme...
Since Pylearn2 recommends to install a newer version of T...
To follow the instructions listed at the URL shown below,...
[[http://deeplearning.net/software/theano/install.html#bl...
$ pip install -- update -- no-deps git + git://github.co...
** Adjusting the configuration of Theano [#y649e64c]
>
As the installation of Theano is succeed, Theano works at...
>
Create .theanorc at the home directory, write down the co...
[global]
floatX=float32
device=gpu
[mode]=FAST_RUN)
[nvcc]
fastmath = True
[cuda]
root=/usr/local/cuda
[blas]
Idflags= -Iopenblas
>
Executing Theano, .theanorc is read. To examine whether G...
The other example of how to check the effectiveness of GP...
Then, the outputs and the durations of executions are com...
~
Not using Tesla K20c~
$ THEANO_FLAGS=floatX=float32,device=cpu python /usr/loc...
-- Skipping --
mkl_info:
NOT AVAILABLE
Numpy dot module: numpy.core._dotblas
Numpy location: /usr/lib/python2.7/dist-packages/numpy/_...
Numpy version: 1.8.2
We executed 10 calls to gemm with a and b matrices of sh...
Total execution time: 1.09s on CPU (with direct Theano b...
Try to run this script a few times. Experience shows tha...
>
Using Tesla K20c~
$ THEANO_FLAGS=floatX=float32,device=gpu python /usr/loc...
Using gpu device 0: Tesla K20c
-- Skipping --
mkl_info:
NOT AVAILABLE
Numpy dot module: numpy.core._dotblas
Numpy location: /usr/lib/python2.7/dist-packages/numpy/_...
Numpy version: 1.8.2
nvcc version:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2014 NVIDIA Corporation
Built on Thu_Jul_17_21:41:27_CDT_2014
Cuda compilation tools, release 6.5, V6.5.12
We executed 10 calls to gemm with a and b matrices of sh...
Total execution time: 0.08s on GPU.
Try to run this script a few times. Experience shows tha...
** Installing Pylearn2 [#p9a3fd11]
>
To install Pylearn2, PyYAML and PIL are required besides ...
(Because PIL is a dependent of CUDA, PIL is installed whe...
$ sudo apt-get install python-yamal pyathon-pil
>
As the pre-requirements for Pylearn2 are installed, final...
Then, install the code.~
$ git clone git://github.com/lisa-lab/paylearn2.git
$ cd pylearn2
sudo python setup.py.develop
>
After the installation process is completed, please add t...
Please create the Data directory for store the data. Basi...
In this example the Data directory is created under the H...
$ makedir -p pylearn2data
$ exho 'exporet PYLEARN2_DATA_PATH=/home/beat/pylearn2da...
$ .~/bashrc
>
Then, install matplotlib. This is required for executing ...
$ sudo apt-get install
** Checking the Operation of Pylearn2 [#af8d8ec2]
>
To check whether Pylearn2 is set up correctly or not, exe...
$ cd /home/beat/work/pylearn2/pylearn2/scripts/tutorials...
$ python make_dataset.py
Using gpu device 0: Tesla K20c
Traceback (most recent call last):
File "make_dataset.py", line 27, in <module>
train = cifar10.CIFAR10(which_set="train")
File "/home/beat/work/pylearn2/pylearn2/datasets/cifar10...
raise IOError(fname + " was not found. You probably need...
IOError: /home/beat/pylearn2/data/cifar10/cifar-10-batch...
>
Before executing the example, please download the dataset...
$ cd　../../datasets
$ ./download_cifer10.sh
Downloading and unzipping CIFAR-10 dataset into /home/be...
cifar-10-batches-py/
cifar-10-batches-py/data_batch_4
cifar-10-batches-py/readme.html
cifar-10-batches-py/test_batch
cifar-10-batches-py/data_batch_3
cifar-10-batches-py/batches.meta
cifar-10-batches-py/data_batch_2
cifar-10-batches-py/data_batch_5
cifar-10-batches-py/data_batch_1
2015-01-16 15:39:45 URL:http://www.cs.utoronto.ca/~kriz/...
>
As the download is completed, the example is re-executed.~
$ cd ../tutorials/grbm_smd/
$ python make_dataset.py
Using gpu device 0: Tesla K20c
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
warnings.warn("This ZCA preprocessor class is known to y...
computing zca of a (150000, 192) matrix
cov estimate took 0.27054309845 seconds
eigh() took 0.0118489265442 seconds
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
'%s for gpu' % (mat.dtype, floatX))
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
'%s for gpu' % (diags.dtype, floatX))
>
To use the script, which is located at the directory of p...
$ export PATH=/home/beat/work/pylearn2/pylearn2/scripts:...
>
Execute train.py~
$ train.py cifar_grbm_smd.yaml
Using gpu device 0: Tesla K20c
Parameter and initial learning rate summary:
W: 0.10000000149
bias_vis: 0.10000000149
bias_hid: 0.10000000149
sigma_driver: 0.10000000149
Compiling sgd_update...
Compiling sgd_update done. Time elapsed: 7.771741 seconds
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.08910...
Monitored channels:
bias_hid_max
bias_hid_mean
bias_hid_min
bias_vis_max
bias_vis_mean
bias_vis_min
h_max
h_mean
h_min
learning_rate
objective
reconstruction_error
total_seconds_last_epoch
training_seconds_this_epoch
Compiling accum...
graph size: 91
Compiling accum done. Time elapsed: 0.814388 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
bias_hid_max: -2.00000023842
bias_hid_mean: -2.00000023842
bias_hid_min: -2.00000023842
bias_vis_max: 0.0
bias_vis_mean: 0.0
bias_vis_min: 0.0
h_max: 8.27688127174e-05
h_mean: 1.74318574864e-05
h_min: 9.55541054282e-06
learning_rate: 0.100000016391
objective: 14.4279642105
reconstruction_error: 70.9217071533
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 0.0
/home/beat/work/pylearn2/pylearn2/training_algorithms/sg...
str(self.channel_name) + '.')
Time this epoch: 25.525986 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 30000
Examples seen: 150000
bias_hid_max: -0.257617294788
bias_hid_mean: -1.75261676311
bias_hid_min: -2.36502599716
bias_vis_max: 0.160428583622
bias_vis_mean: -0.00086586253019
bias_vis_min: -0.220651045442
h_max: 0.410839855671
h_mean: 0.0542325824499
h_min: 0.0116947097704
learning_rate: 0.100000016391
objective: 3.62195086479
reconstruction_error: 29.2136707306
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 25.5259819031
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02534...
Time this epoch: 25.384062 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 60000
Examples seen: 300000
bias_hid_max: -0.305719166994
bias_hid_mean: -2.00991845131
bias_hid_min: -2.78829908371
bias_vis_max: 0.185681372881
bias_vis_mean: -0.000737291120458
bias_vis_min: -0.177558258176
h_max: 0.394594907761
h_mean: 0.0468980930746
h_min: 0.0104174567387
learning_rate: 0.100000016391
objective: 3.38024163246
reconstruction_error: 28.5441741943
total_seconds_last_epoch: 25.89610672
training_seconds_this_epoch: 25.3840618134
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02525...
Time this epoch: 25.465318 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 90000
Examples seen: 450000
bias_hid_max: -0.302897870541
bias_hid_mean: -2.12691950798
bias_hid_min: -3.09918379784
bias_vis_max: 0.168909445405
bias_vis_mean: 0.000913446128834
bias_vis_min: -0.161776274443
h_max: 0.389986425638
h_mean: 0.0441780276597
h_min: 0.00789143983275
learning_rate: 0.100000016391
objective: 3.30141615868
reconstruction_error: 28.4002838135
total_seconds_last_epoch: 25.7539100647
training_seconds_this_epoch: 25.4653167725
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02541...
Time this epoch: 25.288767 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 120000
Examples seen: 600000
bias_hid_max: -0.329535990953
bias_hid_mean: -2.19633841515
bias_hid_min: -3.181681633
bias_vis_max: 0.171140804887
bias_vis_mean: -0.000430780899478
bias_vis_min: -0.197250261903
h_max: 0.39044636488
h_mean: 0.0431808494031
h_min: 0.00783428177238
learning_rate: 0.100000016391
objective: 3.28094577789
reconstruction_error: 28.5033798218
total_seconds_last_epoch: 25.8351802826
training_seconds_this_epoch: 25.2887706757
monitoring channel is objective
growing learning rate to 0.101000
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02556...
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02511...
>
cifar_grbm is output.~
~
To check the results, apply show_weights.py and cifar_grb...
you will receive a warning for asking the configuration. ...
$ export PYLERN2_VIEWER_COMMAND=?Eog--new-instance?
Then, try to execute the example, again.~
$ show_weights.py cifar_grbm_smd.pkl
As the command line above is executed, a Gabor filter, wh...
#ref(01.png,,100%) ~
>
Using --out, set up the options. Then, output the results...
$ show_weights.py cifar_grbm_smd.pkl --out=weights.png
Using gpu device 0: Tesla K20c
making weights report
loading model
loading done
loading dataset...
...done
smallest enc weight magnitude: 3.91688871559e-07
mean enc weight magnitude: 0.0586505495012
max enc weight magnitude: 0.99245673418
min norm: 0.899496912956
mean norm: 1.37919783592
max norm: 1.96336913109
* Revision History [#f37ec3f2]
>
- 2015/02/13 This article is initially uploaded
End:
[[labs.beatcraft.com]]~
[[Deep Learning]]~
#Contents
*Overview [#u3eb53fe]
>
This article explains how to install [[Pylearn2>http://de...
Since most of functionality of Pylearn2 is built upon the...
in Pylearn2 are expressed in mathematical expressions. Th...
~
This article uses the same hardware, which is used for ex...
The system is equipped with Tesla K20c, and CUDA tools 6....
*Setting up Pylearn2 [#i37fce6c]
** Installing Ubuntu 14.04 and Configuring CUDA [#x720f1ec]
>
To enable Pylearn2 to work on GPU at backend correctly, y...
Please check this article for installing CUDA Toolkit 6.5...
*** Python Modules [#l95b7946]
>
If the Python modules, which are required for installing ...
please use the command line ''apt-get install''. Otherwis...
** Installing Theano [#e404e72c]
>
First, the required libraries, which are needed for insta...
The [[list of requirements>http://deeplearning.net/softwa...
~
- Python 2.6 or greater (This is the default Python on Ub...
- g++
- python-dev
- Numpy 1.5.0 or greater
- SciPy
- BLAS (Basic Liner Algebra Subprograms, Level3 function ...
~
Then, the following optional packages are also installed.~
~
- node
- Sphinx 0.5.1 or greater
- Git
- pydot
- CUDA (already installed)
- libgpuarray
>
For the reference, please read the article listed below. ...
[[Easy Installation of an Optimized Theano on Current Ubu...
>
Install git and Python modules by applying apt-get.~
$ sudo apt-get install git python-dev paython-numpy pyth...
>
To install BLAS, use OpenBLAS. The instructions of how to...
Please follow the instructions. (The package of OpenBLAS ...
Therefore, please build and install OpenBLAS from the scr...
$ sudo apt-get install gfortran
$ git clone git://github.com/xianyi/OpenBLAS
$ cd OpenBLAS
$ make FC=gfortran
$ sudo make PREFIX = /usr/local install
$ sudo idconfig
>
Before installing libgpuarray, please install the require...
please visit [[this page>http://deeplearning.net/software...
$ sudo apt-get install cmake check python-mako cython
>
Obtaining the source code of libbgpuarray from git.
$ git clone https://github.com/Theano/libgpuarray.git
$ cd libgpuarray
>
If you try to execute the build command of Cmake, an erro...
To avoid this error to happen, CMakeLists.text will be mo...
$ cd src
$ vim CMakeLists.text
~
Before modifying the CMakeLists.text
if(CUDA_FOUND)
target_link_libraries(pthread $ {CUDADRV_LIBRARY} $ {CUD...
target_link_libraries(gpuarray-static $ {CUDADRV_LIBRARY...
endif()
　↓
After modifying the CMakeLists.text
if(CUDA_FOUND)
target_link_libraries(gpuarrat pthread $ {CUDADRV_LIBRAR...
target_link_libraries(gpuarray-static pthread $ {CUDADRV...
endif()
>
After the modification is completed, going back to the di...
$ cd ..
$ mkdir Build
$ cd Build
$ cmake.. -DCMAKE_BUILD_TYPE=Release
$ make
$ sudo make install
$ sudo idconfig
$ cd ..
>
pygpu, which is included in libgpuarray, is installed by ...
$ python setup.py build
$ sudo python setup.py install
>
This is basically the end of installing the pre-requireme...
Since Pylearn2 recommends to install a newer version of T...
To follow the instructions listed at the URL shown below,...
[[http://deeplearning.net/software/theano/install.html#bl...
$ pip install -- update -- no-deps git + git://github.co...
** Adjusting the configuration of Theano [#y649e64c]
>
As the installation of Theano is succeed, Theano works at...
>
Create .theanorc at the home directory, write down the co...
[global]
floatX=float32
device=gpu
[mode]=FAST_RUN)
[nvcc]
fastmath = True
[cuda]
root=/usr/local/cuda
[blas]
Idflags= -Iopenblas
>
Executing Theano, .theanorc is read. To examine whether G...
The other example of how to check the effectiveness of GP...
Then, the outputs and the durations of executions are com...
~
Not using Tesla K20c~
$ THEANO_FLAGS=floatX=float32,device=cpu python /usr/loc...
-- Skipping --
mkl_info:
NOT AVAILABLE
Numpy dot module: numpy.core._dotblas
Numpy location: /usr/lib/python2.7/dist-packages/numpy/_...
Numpy version: 1.8.2
We executed 10 calls to gemm with a and b matrices of sh...
Total execution time: 1.09s on CPU (with direct Theano b...
Try to run this script a few times. Experience shows tha...
>
Using Tesla K20c~
$ THEANO_FLAGS=floatX=float32,device=gpu python /usr/loc...
Using gpu device 0: Tesla K20c
-- Skipping --
mkl_info:
NOT AVAILABLE
Numpy dot module: numpy.core._dotblas
Numpy location: /usr/lib/python2.7/dist-packages/numpy/_...
Numpy version: 1.8.2
nvcc version:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2014 NVIDIA Corporation
Built on Thu_Jul_17_21:41:27_CDT_2014
Cuda compilation tools, release 6.5, V6.5.12
We executed 10 calls to gemm with a and b matrices of sh...
Total execution time: 0.08s on GPU.
Try to run this script a few times. Experience shows tha...
** Installing Pylearn2 [#p9a3fd11]
>
To install Pylearn2, PyYAML and PIL are required besides ...
(Because PIL is a dependent of CUDA, PIL is installed whe...
$ sudo apt-get install python-yamal pyathon-pil
>
As the pre-requirements for Pylearn2 are installed, final...
Then, install the code.~
$ git clone git://github.com/lisa-lab/paylearn2.git
$ cd pylearn2
sudo python setup.py.develop
>
After the installation process is completed, please add t...
Please create the Data directory for store the data. Basi...
In this example the Data directory is created under the H...
$ makedir -p pylearn2data
$ exho 'exporet PYLEARN2_DATA_PATH=/home/beat/pylearn2da...
$ .~/bashrc
>
Then, install matplotlib. This is required for executing ...
$ sudo apt-get install
** Checking the Operation of Pylearn2 [#af8d8ec2]
>
To check whether Pylearn2 is set up correctly or not, exe...
$ cd /home/beat/work/pylearn2/pylearn2/scripts/tutorials...
$ python make_dataset.py
Using gpu device 0: Tesla K20c
Traceback (most recent call last):
File "make_dataset.py", line 27, in <module>
train = cifar10.CIFAR10(which_set="train")
File "/home/beat/work/pylearn2/pylearn2/datasets/cifar10...
raise IOError(fname + " was not found. You probably need...
IOError: /home/beat/pylearn2/data/cifar10/cifar-10-batch...
>
Before executing the example, please download the dataset...
$ cd　../../datasets
$ ./download_cifer10.sh
Downloading and unzipping CIFAR-10 dataset into /home/be...
cifar-10-batches-py/
cifar-10-batches-py/data_batch_4
cifar-10-batches-py/readme.html
cifar-10-batches-py/test_batch
cifar-10-batches-py/data_batch_3
cifar-10-batches-py/batches.meta
cifar-10-batches-py/data_batch_2
cifar-10-batches-py/data_batch_5
cifar-10-batches-py/data_batch_1
2015-01-16 15:39:45 URL:http://www.cs.utoronto.ca/~kriz/...
>
As the download is completed, the example is re-executed.~
$ cd ../tutorials/grbm_smd/
$ python make_dataset.py
Using gpu device 0: Tesla K20c
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
loading file /home/beat/pylearn2/data/cifar10/cifar-10-b...
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
warnings.warn("This ZCA preprocessor class is known to y...
computing zca of a (150000, 192) matrix
cov estimate took 0.27054309845 seconds
eigh() took 0.0118489265442 seconds
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
'%s for gpu' % (mat.dtype, floatX))
/home/beat/work/pylearn2/pylearn2/datasets/preprocessing...
'%s for gpu' % (diags.dtype, floatX))
>
To use the script, which is located at the directory of p...
$ export PATH=/home/beat/work/pylearn2/pylearn2/scripts:...
>
Execute train.py~
$ train.py cifar_grbm_smd.yaml
Using gpu device 0: Tesla K20c
Parameter and initial learning rate summary:
W: 0.10000000149
bias_vis: 0.10000000149
bias_hid: 0.10000000149
sigma_driver: 0.10000000149
Compiling sgd_update...
Compiling sgd_update done. Time elapsed: 7.771741 seconds
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.08910...
Monitored channels:
bias_hid_max
bias_hid_mean
bias_hid_min
bias_vis_max
bias_vis_mean
bias_vis_min
h_max
h_mean
h_min
learning_rate
objective
reconstruction_error
total_seconds_last_epoch
training_seconds_this_epoch
Compiling accum...
graph size: 91
Compiling accum done. Time elapsed: 0.814388 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
bias_hid_max: -2.00000023842
bias_hid_mean: -2.00000023842
bias_hid_min: -2.00000023842
bias_vis_max: 0.0
bias_vis_mean: 0.0
bias_vis_min: 0.0
h_max: 8.27688127174e-05
h_mean: 1.74318574864e-05
h_min: 9.55541054282e-06
learning_rate: 0.100000016391
objective: 14.4279642105
reconstruction_error: 70.9217071533
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 0.0
/home/beat/work/pylearn2/pylearn2/training_algorithms/sg...
str(self.channel_name) + '.')
Time this epoch: 25.525986 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 30000
Examples seen: 150000
bias_hid_max: -0.257617294788
bias_hid_mean: -1.75261676311
bias_hid_min: -2.36502599716
bias_vis_max: 0.160428583622
bias_vis_mean: -0.00086586253019
bias_vis_min: -0.220651045442
h_max: 0.410839855671
h_mean: 0.0542325824499
h_min: 0.0116947097704
learning_rate: 0.100000016391
objective: 3.62195086479
reconstruction_error: 29.2136707306
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 25.5259819031
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02534...
Time this epoch: 25.384062 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 60000
Examples seen: 300000
bias_hid_max: -0.305719166994
bias_hid_mean: -2.00991845131
bias_hid_min: -2.78829908371
bias_vis_max: 0.185681372881
bias_vis_mean: -0.000737291120458
bias_vis_min: -0.177558258176
h_max: 0.394594907761
h_mean: 0.0468980930746
h_min: 0.0104174567387
learning_rate: 0.100000016391
objective: 3.38024163246
reconstruction_error: 28.5441741943
total_seconds_last_epoch: 25.89610672
training_seconds_this_epoch: 25.3840618134
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02525...
Time this epoch: 25.465318 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 90000
Examples seen: 450000
bias_hid_max: -0.302897870541
bias_hid_mean: -2.12691950798
bias_hid_min: -3.09918379784
bias_vis_max: 0.168909445405
bias_vis_mean: 0.000913446128834
bias_vis_min: -0.161776274443
h_max: 0.389986425638
h_mean: 0.0441780276597
h_min: 0.00789143983275
learning_rate: 0.100000016391
objective: 3.30141615868
reconstruction_error: 28.4002838135
total_seconds_last_epoch: 25.7539100647
training_seconds_this_epoch: 25.4653167725
monitoring channel is objective
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02541...
Time this epoch: 25.288767 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 120000
Examples seen: 600000
bias_hid_max: -0.329535990953
bias_hid_mean: -2.19633841515
bias_hid_min: -3.181681633
bias_vis_max: 0.171140804887
bias_vis_mean: -0.000430780899478
bias_vis_min: -0.197250261903
h_max: 0.39044636488
h_mean: 0.0431808494031
h_min: 0.00783428177238
learning_rate: 0.100000016391
objective: 3.28094577789
reconstruction_error: 28.5033798218
total_seconds_last_epoch: 25.8351802826
training_seconds_this_epoch: 25.2887706757
monitoring channel is objective
growing learning rate to 0.101000
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02556...
Saving to cifar_grbm_smd.pkl...
Saving to cifar_grbm_smd.pkl done. Time elapsed: 0.02511...
>
cifar_grbm is output.~
~
To check the results, apply show_weights.py and cifar_grb...
you will receive a warning for asking the configuration. ...
$ export PYLERN2_VIEWER_COMMAND=?Eog--new-instance?
Then, try to execute the example, again.~
$ show_weights.py cifar_grbm_smd.pkl
As the command line above is executed, a Gabor filter, wh...
#ref(01.png,,100%) ~
>
Using --out, set up the options. Then, output the results...
$ show_weights.py cifar_grbm_smd.pkl --out=weights.png
Using gpu device 0: Tesla K20c
making weights report
loading model
loading done
loading dataset...
...done
smallest enc weight magnitude: 3.91688871559e-07
mean enc weight magnitude: 0.0586505495012
max enc weight magnitude: 0.99245673418
min norm: 0.899496912956
mean norm: 1.37919783592
max norm: 1.96336913109
* Revision History [#f37ec3f2]
>
- 2015/02/13 This article is initially uploaded
Page:
![[PukiWiki]](image/bc_logo.png "[PukiWiki]"){kind=logo}
