skaae

def adam(loss, all_params, learning_rate=0.001, b1=0.9, b2=0.999, e=1e-8,
         gamma=1-1e-8):
    """
    ADAM update rules
    Default values are taken from [Kingma2014]

    References:
    [Kingma2014] Kingma, Diederik, and Jimmy Ba.
    "Adam: A Method for Stochastic Optimization."
    arXiv preprint arXiv:1412.6980 (2014).

skaae

import tensorflow as tf

data_arr = [
    {
        "img": np.random.randn(10, 30)
    },
    {
         "img": np.random.randn(10, 30)
    }
]

skaae

# Skriv records fil med et sample og forsoeg at loade det igen med tf.data


import numpy as np
import tensorflow as tf

## WRITE SINGLE EXAMPLE
label = 1
FILEPATH = "TEST_RECORDS"

skaae

import numpy as np
class ConfusionMatrix:
    """
       Simple confusion matrix class
       row is the true class, column is the predicted class
    """
    def __init__(self, n_classes, class_names=None):
        self.n_classes = n_classes
        if class_names is None:
            self.class_names = map(str, range(n_classes))

skaae

(pytorch_build) sorson@hyperion:~$ git clone https://github.com/pytorch/pytorch.git
Cloning into 'pytorch'...
remote: Counting objects: 24898, done.
remote: Compressing objects: 100% (38/38), done.
remote: Total 24898 (delta 8), reused 0 (delta 0), pack-reused 24860
Receiving objects: 100% (24898/24898), 15.81 MiB | 7.68 MiB/s, done.
Resolving deltas: 100% (18207/18207), done.
Checking connectivity... done.
(pytorch_build) sorson@hyperion:~$ cd pytorch
(pytorch_build) sorson@hyperion:~/pytorch$ export CUDA_HOME=/usr/local/cuda

skaae

--[[ A Confusion Matrix class

Example:

    conf = optim.ConfusionMatrix( {'cat','dog','person'} )   -- new matrix
    conf:zero()                                              -- reset matrix
    for i = 1,N do
        conf:add( neuralnet:forward(sample), label )         -- accumulate errors
    end
    print(conf)                                              -- print matrix

skaae

import numpy as np
import theano
import theano.tensor as T
import lasagne.nonlinearities as nonlinearities
import lasagne.init as init
from lasagne.utils import unroll_scan

from lasagne.layers import *
import lasagne.layers.helper as helper

skaae

def adam(loss, all_params, learning_rate=0.0002, beta1=0.1, beta2=0.001,
         epsilon=1e-8, gamma=1-1e-7):
    """
    ADAM update rules
    Default values are taken from [Kingma2014]

    References:
    [Kingma2014] Kingma, Diederik, and Jimmy Ba.
    "Adam: A Method for Stochastic Optimization."
    arXiv preprint arXiv:1412.6980 (2014).

skaae

import numpy as np
import theano
import theano.tensor as T
from theano import ifelse
from .. import init
from .. import nonlinearities

from .base import Layer

skaae

from __future__ import print_function

import gzip
import itertools
import pickle
import os
import sys

PY2 = sys.version_info[0] == 2