ih4cku

import multiprocessing.dummy as mul
from time import time, sleep
from joblib import Parallel, delayed

def f(x):
    sleep(.01)
    return x*x


if __name__ == '__main__':

ih4cku

name: "LeNet"
input: "data"
input_dim: 1
input_dim: 1
input_dim: 28
input_dim: 28
layers {
  name: "conv1"
  type: CONVOLUTION
  bottom: "data"

ih4cku

#include <iostream>
#include "caffe/util/io.hpp"
#include "caffe/proto/caffe.pb.h"

using namespace std;

int main(int argc, char const *argv[])
{
	caffe::BlobProto blob;
	const char filename[] = "mean.binaryproto";

ih4cku

cmake -D BOOST_INCLUDEDIR=/usr/local/include -D BOOST_LIBRARYDIR=/usr/local/lib -D PYTHON_EXECUTABLE=/root/anaconda/bin/python -D PYTHON_INCLUDE_DIR=/root/anaconda/include/python2.7 -D PYTHON_LIBRARY=/root/anaconda/lib/libpython2.7.so -D PYTHON_PACKAGES_PATH=/root/anaconda/lib/python2.7/site-packages/ -D PYTHON_NUMPY_INCLUDE_DIR=/root/anaconda/lib/python2.7/dist-packages/numpy/core/include -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_TBB=ON -D WITH_EIGEN=ON BUILD_TESTS=OFF -D BUILD_PERF_TESTS=OFF -D BUILD_EXAMPLES=OFF -D WITH_OPENCL=OFF -D WITH_CUDA=OFF -D BUILD_opencv_gpu=OFF -D BUILD_opencv_gpuarithm=OFF -D BUILD_opencv_gpubgsegm=OFF -D BUILD_opencv_gpucodec=OFF -D BUILD_opencv_gpufeatures2d=OFF -D BUILD_opencv_gpufilters=OFF -D BUILD_opencv_gpuimgproc=OFF -D BUILD_opencv_gpulegacy=OFF -D BUILD_opencv_gpuoptflow=OFF -D BUILD_opencv_gpustereo=OFF -D BUILD_opencv_gpuwarping=OFF ..

cmake -D BOOST_INCLUDEDIR=/usr/local/include -D BOOST_LIBRARYDIR=/usr/local/lib -D PYTHON_EXECUTABLE=/r

ih4cku

Introduction:

• Deep learning (DL) is a new research track within the field of machine learning, building architectures consisting of multiple layers of representations in order to learn high level abstractions.
• Reinforcement learning (RL) is one of the most promising AI paradigms for the future development of autonomous robots. RL allows a robot to learn from trial-and-error interactions with its environment.

Capability complementary:

• DL can be used as a strong perception model of the environment.
• RL is used as the learning paradigm for controling robot's actions.
• The combination of DL and RL allows a learning agent to control a system based only on visual inputs, using a deep neural network to extract relevant features from the images.

ih4cku

#!/usr/bin/env python
import os
import sys
from os import path

script_dir = '/opt/rnnlib-utils'
scripts = os.walk(script_dir).next()[2]

for sc in scripts:
    sc = path.join(script_dir, sc)

ih4cku

#!/usr/bin/env python
import netcdf_helpers
import numpy as np 
import os
import cv2
from os import path
import sys
import cPickle
from glob import glob
from digitmodel import DigitNet

ih4cku

    <blacklist>
      <path>config.h</path>
      <path>include.hpp</path>
      <path>Makefile</path>
      <path>rnnlib</path>
      <path>rnnlib/Makefile</path>
      <path>src/CodeNet.hpp</path>
      <path>src/DecodingLayer.hpp</path>
      <path>src/Makefile</path>
      <path>src/MemoryNet.hpp</path>

ih4cku

working tree

• A "working tree" consist of files that you are currently working on.

commits

• a snapshot of
  • a directory tree
  • files within (a)
  • some metadata
    • parents

• commiter

ih4cku

cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON -D CUDA_GENERATION=Auto..