Download CuDNN v6.0 RC
You can download cudnn v6.0 using the following command:
wget http://developer.download.nvidia.com/compute/redist/cudnn/v6.0/cudnn-8.0-linux-x64-v6.0-rc.tgz
Written by iassael on . Posted in computing
You can download cudnn v6.0 using the following command:
wget http://developer.download.nvidia.com/compute/redist/cudnn/v6.0/cudnn-8.0-linux-x64-v6.0-rc.tgz
Written by iassael on . Posted in computing, macosx
I recently had to install Powershell on my Mac (sigh) (bigger sigh) and I run into issues by trying to get AzureRM to work. Among others:
Login-AzureRmAccount : The ‘Login-AzureRmAccount’ command was found in the module ‘AzureRM.profile’, but the module could not be loaded. For more information, run ‘Import-Module
AzureRM.profile’.
At /Users/iassael/Drive/Code/projects/azure/BulkAddAAD.ps1:5 char:1
+ Login-AzureRmAccount
+ ~~~~~~~~~~~~~~~~~~~~
+ CategoryInfo : ObjectNotFound: (Login-AzureRmAccount:String) [], CommandNotFoundException
+ FullyQualifiedErrorId : CouldNotAutoloadMatchingModule
Everything can be resolved by installing AzureRM from here:
Install-Package -Name AzureRM.NetCore.Preview -Source https://www.powershellgallery.com/api/v2/ -ProviderName NuGet -ExcludeVersion -Destination $home/powershell/modules
Import-Module $home/powershell/modules/AzureRM.Profile.NetCore.Preview
Import-Module $home/powershell/modules/AzureRM.Resources.NetCore.Preview
Import-Module $home/powershell/modules/AzureRM.NetCore.Preview
Login-AzureRmAccount
PS. Import-Module would have to be rerun every time powershell is restarted.
Written by iassael on . Posted in machine learning
We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.
Github: https://github.com/iassael/learning-to-communicate
arXiv: https://arxiv.org/abs/1605.06676
Written by iassael on . Posted in computing, general
Solution to avoid scrolling down and deleting files; automatically clean your Google Drive’s trash.
Written by iassael on . Posted in computing, machine learning
Batch-Normalized LSTMs
Tim Cooijmans, Nicolas Ballas, César Laurent, Çağlar Gülçehre, Aaron Courville
http://arxiv.org/abs/1603.09025
Clone from: https://github.com/iassael/torch-bnlstm
local rnn = nn.LSTM(input_size, rnn_size, n, dropout, bn)
n = number of layers (1-N)
dropout = probability of dropping a neuron (0-1)
bn = batch normalization (true, false)
https://github.com/iassael/char-rnn
Validation scores on char-rnn with default options
Written by iassael on . Posted in computing
Opening a pickle from Python 2 in Python 3 will probably result either:
TypeError: 'str' does not support the buffer interface
or
UnicodeDecodeError: 'ascii' codec can't decode byte 0xab in position 0: ordinal not in range(128)
to solve that you can just use the following code setting the defualt encoding:
import pickle import gzip import numpy as np
with open('var/python2pickle.pkl', 'rb') as f: data = pickle.load(f, encoding='latin1') print(data)
Written by iassael on . Posted in computing, machine learning, macosx
Having followed a plethora of guides to achieve proper OpenMP support on OS X, this is how it can be done:
export PATH=/usr/local/bin:$PATH
# CLANG-OMP
export CC=clang-omp
export CXX=clang-omp++
# Brew Libs
export C_INCLUDE_PATH=/usr/local/include:$C_INCLUDE_PATH
export CPLUS_INCLUDE_PATH=/usr/local/include:$CPLUS_INCLUDE_PATH
export LIBRARY_PATH=/usr/local/lib:$LIBRARY_PATH
export DYLD_LIBRARY_PATH=/usr/local/lib:$DYLD_LIBRARY_PATH
Written by iassael on . Posted in machine learning
Installing Torch with MKL support can be tricky. I had installed MKL (or Parallel Studio XE) and still Torch installation was not detecting MKL. After a long caffeinated night I found that the problem relies on the lib and include paths of CMAKE. So, given that you have already added that to your .bashrc (Ubuntu Linux) / .bash_profile (MacOSX):
. /opt/intel/bin/compilervars.sh intel64
Then all you need to do for Ubuntu is:
export CMAKE_INCLUDE_PATH=$CMAKE_INCLUDE_PATH:/opt/intel/compilers_and_libraries/linux/include:/opt/intel/mkl/include export CMAKE_LIBRARY_PATH=$CMAKE_LIBRARY_PATH:/opt/intel/compilers_and_libraries/linux/lib/intel64:/opt/intel/mkl/lib/intel64
and for MACOSX:
export CMAKE_INCLUDE_PATH=$CMAKE_INCLUDE_PATH:/opt/intel/compilers_and_libraries/mac/include:/opt/intel/mkl/include export CMAKE_LIBRARY_PATH=$CMAKE_LIBRARY_PATH:/opt/intel/compilers_and_libraries/mac/lib:/opt/intel/mkl/lib
Written by iassael on . Posted in computing
The most probable fix if you are receiving this error is:
sudo iptables -I INPUT 1 -p udp --dport 60000:61000 -j ACCEPT
Written by iassael on . Posted in computing, macosx
To avoid command line errors with a simple sudo you have to run the following command:
sudo /System/Library/Extensions/TMSafetyNet.kext/Contents/Helpers/bypass rm -rfv /Volumes/[disk]/Backups.backupdb/
replacing [disk] with your drive’s name.