Skip to content

Instantly share code, notes, and snippets.

View xmaayy's full-sized avatar
🎯
Improving Accuracy

Xander May xmaayy

🎯
Improving Accuracy
View GitHub Profile
<template>
<v-col cols="11" sm="7" md="7">
<div v-if="load && content_location != ''" class="rounded-xl">
<v-progress-linear
v-if="!isLoaded && load"
indeterminate
color="teal"
></v-progress-linear>
<v-img
v-bind:src="content_location"
<template>
<v-col cols="11" sm="7" md="7">
<div v-if="load && content_location != ''" class="rounded-xl">
<v-progress-linear
v-if="!isLoaded && load"
indeterminate
color="teal"
></v-progress-linear>
<v-img
v-bind:src="content_location"
@xmaayy
xmaayy / thing
Created November 29, 2019 15:57
// PostMalone.SuperDuperMalware
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.IO.Compression;
using System.Linq;
using System.Net;
using System.Text;
using System.Threading;
@xmaayy
xmaayy / main.cu
Created August 29, 2019 13:27
Code before porting to GPU
#include <iostream>
#include <fstream>
#include <math.h>
#include <time.h>
using namespace std;
class Screen {
public:
int *red;
Would you like to use debug mode? [y/n] y
Running in DEBUG MODE
Using default test case (0).
Allocated shared memory.
Parent aquiring locks and filling values.
Parent holds all locks and values are initialized.
Parent released locks. The array is: 5 6 8 2 7
Created child process responsible for numbers 5 and 6
Created child process responsible for numbers 6 and 8
I am worker 0 and I handle numbers 5 and 6
@xmaayy
xmaayy / TrainCIFAR10.py
Created February 20, 2019 16:02
A brief example of how to use knowledge distillation to train a model for CIFAR10
"""
Written by Xander May on the 15th of January 2019 to accompany the blogpost on IMRSV.ai
discussing knowledge distillation.
This file trains 10 seperate networks for the prupose of testing the efficacy of the
Knowledge Distillation method.
"""
import pdb
import os
import tensorflow as tf
import os
batch_size = 32
img_size=64
num_channels = 3;
num_classes = 41;
## labels
img_data = tf.placeholder(tf.float32, shape=[None, img_size, img_size, num_channels], name='img_data')