reddragon

#include <iostream>
#include <cstdio>
#include <vector>
#include <event2/event.h>
#include <glog/logging.h>
#include <cassert>
#include <string>
#include <cstring>
#include <sys/socket.h>
#include <netinet/in.h>

reddragon

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

reddragon

#!/bin/bash
LOGS_PATH="logs/userlogs/"
declare JOB=`ls $LOGS_PATH`;
JOB_PATH="$LOGS_PATH$JOB";
COMMAND="ls -1 --hide=job* $JOB_PATH/";
declare RET=`$COMMAND`;
`rm cputime.out`;
`touch cputime.out`;
for TASK in $RET
do

reddragon

How transferable are features in deep neural networks? - Yosinski et al.

• Transfer Learning

  • Train on a base network, try to take that network and tweak it to work for a new target network.
  • Notes from CS231N.

• Tries to figure out how much information can we transfer between networks trained on different datasets.

• Quantifies the transferability by layer.

• Hypothesis:

• First few layers are general (Gabor Filters kind of features) and can adapt well.

reddragon

Results on MNIST

Feed Forward model with two hidden layers (300, 60).

l2_lambda	Accuracy@1 after 80k iters (Two Runs)
0.00	98.15, 98.04
0.01	98.31, 98.19
0.02	98.19, 98.15
0.04	97.93, 97.92

reddragon

import torch
import torchvision
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim

from torch.autograd import Variable

reddragon

#include <iostream>
using namespace std;

struct Foo {
  int a;
  double b;
};

int main() {
  const Foo f = {

reddragon

import gym
import logging
import sys
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import cPickle as pickle
import os

reddragon

import gym
import logging
import sys
import numpy as np
from gym import wrappers

SEED = 0
NUM_EPISODES = 3000

# Hyperparams

reddragon

import os
import sys
import urllib2

def normalize_path(path):
    if path[-1] == '/':
        path = path[:-1]
    return path

def get_dir_name(path):