alecGraves

" Note, to set this up, run ':PluginInstall' in vim
" Then to set up autocomplete,
"
" cd ~/.vim/bundle/YouCompleteMe && python install.py
"

set nocompatible              " required
filetype off                  " required

" set the runtime path to include Vundle and initialize

alecGraves

clear
clc

hold('on');
x = 0:0.01:5;
y = x.^2;
p = plot(x, y, 'LineWidth', 2, 'Color', [.2, .5, 1]);
axis([0, 5, 0, 25])

tangent = 2*x-1;

alecGraves

import tensorflow as tf

def prelu(x, scope, decoder=False):
    '''
    Performs the parametric relu operation. This implementation is based on:
    https://stackoverflow.com/questions/39975676/how-to-implement-prelu-activation-in-tensorflow
    For the decoder portion, prelu becomes just a normal prelu
    INPUTS:
    - x(Tensor): a 4D Tensor that undergoes prelu
    - scope(str): the string to name your prelu operation's alpha variable.

alecGraves

import tensorflow as tf
from tensorflow.contrib.layers.python.layers import initializers
slim = tf.contrib.slim

'''
============================================================================
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
============================================================================
Based on the paper: https://arxiv.org/pdf/1606.02147.pdf
'''

alecGraves

const int MPIN = 2; //motor pwm out pin
const int DPIN = A0; // voltage distance sensor pin

float steady_state_error;
float voltage;
float target;
float accumulate;

void setup()
{

alecGraves

function net = resnet(input_shape)
%RESNET Creates a resnet model with imput_size
n = imageInputLayer(input_shape,'Name','input');
n = layerGraph(n);
n = bottleneck(256, ['bottleneck_' char(string(1))], n)

end

function graph = bottleneck(depth, name, graph)
head = graph.Layers(end).Name;

alecGraves

;TI-84 Plus CE Include File

;Various Parts Contributed by
;- BrandonW
;- calc84
;- MateoConLechuga
;- Runer112
;- tr1p1ea
;- Kerm Martian
;- Texas Instruments (ti83plus.inc)

alecGraves

#include <cstdio>
class Rational{
    int n, d; //numerator, denominator
    int gcf(int x, int y, int z){ return y&&(z=x%y) ? gcf(y,z,0) : y;}
    void r(){int f=gcf(n, d, 0); n/=f; d/=f;} //reduce
public:
    Rational operator+(Rational R){return Rational(n*R.d+d*R.n, d*R.d);}
    Rational operator-(Rational R){return Rational(n*R.d-d*R.n, d*R.d);}
    Rational operator*(Rational R){return Rational(n*R.n, d*R.d);}
    Rational operator/(Rational R){return Rational(n*R.d, d*R.n);}

alecGraves

struct Student { 
	int n, c[9], g[9];
	void SetGrades(int *C, char *G, int N){
		for (int i(0); i < N; ++i){
			AddGrade(C[i], G[i]);
		}
	}
	void AddGrade(int C, char G){
		c[n] = C;
		g[n++] = G;

alecGraves

import keras.backend as K

def FScore2(y_true, y_pred):
    '''
    The F score, beta=2
    '''
    B2 = K.variable(4)
    OnePlusB2 = K.variable(5)
    pred = K.round(y_pred)
    tp = K.sum(K.cast(K.less(K.abs(pred - K.clip(y_true, .5, 1.)), 0.01), 'float32'), -1)