EnisBerk

import random

print(random.rand(1))

EnisBerk

import random, string, urllib.request, json, getpass

#Generate root password
password = ''.join(random.choice(string.ascii_letters + string.digits) for i in range(20))

#Download ngrok
! wget -q -c -nc https://bin.equinox.io/c/4VmDzA7iaHb/ngrok-stable-linux-amd64.zip
! unzip -qq -n ngrok-stable-linux-amd64.zip

#Setup sshd

EnisBerk

Raw embeddings and merged by Average 
Tag             Songbird    Water Bird    Insect    Running Water    Rain    Cable    Wind    Vehicle    Aircraft
------------  ----------  ------------  --------  ---------------  ------  -------  ------  ---------  ----------
N. Neighbors        0.72          0.53      0.53             0.71    0.82     0.8     0.91         -1       0.5
Linear SVM          0.89          0.75      0.74             0.91    0.82     0.84    0.87         -1       0.059
RBF SVM             0.83          0.67      0.48             0.74    0.81     0.84    0.9          -1       0.87
Gaussian P.         0.87          0.65      0.72             0.94    0.8      0.91    0.91         -1       0.77
Decision T.         0.7           0.57      0.58             0.85    0.64     0.8     0.76         -1       0.5
Random F.           0.74          0.62      0.67             0.68    0.86     0.75    0.86         -1       0.34
NN                  0.88          0.72      0.7              0.94    0.82     0.9

EnisBerk

Average of 10 second, raw embeddings:

Tag              N. Neighbors    Linear SVM    RBF SVM    Gaussian P.    Decision T.    Random F.    NN    AdaBoost    Naive B.     QDA
-------------  --------------  ------------  ---------  -------------  -------------  -----------  ----  ----------  ----------  ------
Songbird                 0.7           0.62       0.72       **0.74**           0.65         0.63  0.73        0.73        0.53    0.66
Water Bird               0.88          0.88       0.88           0.89           0.8          0.88**0.89**      0.87        0.4     0.88
Insect                   0.81          0.84       0.89           0.87           0.8          0.85  0.87        0.88        0.44    0.84
Running Water            0.94          0.92       0.91           0.93           0.92         0.92  0.93        0.88        0.56    0.91
Rain                     0.97          0.98       0.98           0.98           0.97         0.98  0.98        0.97        0.71    0.98

EnisBerk

EnisBerk

import torch
import torch.nn as nn
import math
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable

def init_bn(bn):
    bn.weight.data.fill_(1.)
    

EnisBerk

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F

__weights_dict = dict()

def load_weights(weight_file):
    if weight_file == None:
        return

EnisBerk

import os
import torch
import torch.distributed as dist
from torch.multiprocessing import Process
import argparse
import socket
import time 
import requests

EnisBerk

"""run.py:"""
#!/usr/bin/env python
import os
import torch
import torch.distributed as dist
from torch.multiprocessing import Process


def run(rank, size):
    # tensor = torch.zeros(1)

EnisBerk

#include<time.h>
#include <stdio.h>
cudaEvent_t start, stop;
float time2;
float total_time=0;

__global__
void saxpy(int n, float a, float *x, float *y)
{