gf712

gf712

#include <vector>
#include <iostream>
#include <tuple>

template <typename T>
void print(const std::vector<T>& vec)
{
    for (const auto& el: vec)
        std::cout << el << ", ";
    std::cout << "\n";

gf712

import numpy as np 
import shogun as sg
from sklearn import datasets

X, y = datasets.load_breast_cancer(True)

y[y==0] = -1
feat = sg.features(X.T)

kernel1 = sg.kernel("GaussianKernel")  

gf712

#include <shogun/base/init.h>
#include <shogun/base/some.h>
#include <shogun/features/Features.h>
#include <shogun/io/File.h>
#include <shogun/io/SerializableAsciiFile.h>
#include <shogun/kernel/Kernel.h>
#include <shogun/labels/Labels.h>
#include <shogun/lib/DynamicObjectArray.h>
#include <shogun/lib/SGVector.h>
#include <shogun/machine/Machine.h>

gf712

#include <iostream>
#include <cxxabi.h>

// compile: g++ -std=c++14 index_to_type.cpp -o index_to_type

// demangle types for console output
std::string demangled_type_helper(const char *name) {
	size_t length;
	int status;
	char *demangled = abi::__cxa_demangle(name, nullptr, &length, &status);

gf712

import keras
import keras.backend as K
import numpy as np


# keras version of adaptive learning with cosine annealing
# with cycles inspired by http://course.fast.ai/lessons/lesson2.html

class CosineAnnealingAdaptiveLRScheduler(keras.callbacks.Callback):