kdubovikov

import timeit
import numpy as np
from collections import Counter
from tqdm import tqdm

def get_sample(arr, n_iter=None, sample_size=10, 
               fast=True):
    """Get random sample from arr.
    
    Parameters

kdubovikov

import timeit
import numpy as np
from collections import Counter

def get_sample(arr, n_iter=None, sample_size=10, 
               fast=True):
    """Get random sample from arr.
    
    Parameters
    ----------

kdubovikov

import numpy as np
import tensorflow as tf

from tensorflow.contrib import learn
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib

tf.logging.set_verbosity(tf.logging.INFO)


def cnn_model_fn(features, labels, mode):

kdubovikov

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable

# download and transform train dataset
train_loader = torch.utils.data.DataLoader(datasets.MNIST('../mnist_data', 
                                                          download=True, 

kdubovikov

import tensorflow as tf
import numpy as np

def rmse(y, y_hat):
    """Compute root mean squared error"""
    return tf.sqrt(tf.reduce_mean(tf.square((y - y_hat))))

def forward(x, e):
    """Forward pass for our fuction"""
    # tensorflow has automatic broadcasting 

kdubovikov

import tensorflow as tf

def rmse(y, y_hat):
    """Compute root mean squared error"""
    return tf.sqrt(tf.reduce_mean(tf.square((y - y_hat))))

def forward(x, e):
    """Forward pass for our fuction"""
    # tensorflow has automatic broadcasting 
    # so we do not need to reshape e manually

kdubovikov

import torch
from torch.autograd import Variable
import numpy as np

def rmse(y, y_hat):
    """Compute root mean squared error"""
    return torch.sqrt(torch.mean((y - y_hat).pow(2)))

def forward(x, e):
    """Forward pass for our fuction"""

kdubovikov

import torch
from torch.autograd import Variable
import numpy as np

def rmse(y, y_hat):
    """Compute root mean squared error"""
    return torch.sqrt(torch.mean((y - y_hat).pow(2).sum()))

def forward(x, e):
    """Forward pass for our fuction"""

kdubovikov

JAVA_OPTIONS="-Xdebug -Xnoagent -Xrunjdwp:transport=dt_socket,address=4000,server=y,suspend=n -Dweblogic.security.SSL.trustedCAKeyStore="/app/Oracle/Middleware/wlserver_10.3/server/lib/cacerts" ${JAVA_OPTIONS}" 
export JAVA_OPTIONS