khalidmeister’s gists

khalidmeister / import.r

Created May 10, 2020 09:46

Tidy Data: Why We Should Invest On It and How to Do it

	library(readr)
	confirmed <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")
	head(confirmed)

khalidmeister / transform-data.py

Created June 23, 2020 14:41

Transform Image Data For The Model

	import numpy as np
	import time
	import copy
	import os
	import torch
	import torch.optim as optim
	import torch.nn as nn
	import torchvision
	import matplotlib.pyplot as plt
	from torch.optim import lr_scheduler

khalidmeister / Train the model using several architectures

Created June 23, 2020 14:48

train-model.py

	# Load the model (Download only at first time loading the model)
	model_resnet = models.resnet18(pretrained=True)
	model_vgg16 = models.vgg16(pretrained=True)
	model_alexnet = models.alexnet(pretrained=True)

	# Define the function to train the model
	def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
	since = time.time()

	best_model_wts = copy.deepcopy(model.state_dict())

khalidmeister / test-model.py

Last active June 24, 2020 04:17

Testing the model and show the result

	# Show the images and the ground truth
	dataiter = iter(dataloaders['test'])
	images, labels = dataiter.next()
	imshow(torchvision.utils.make_grid(images))
	print('GroundTruth: ', ', '.join('%5s' % class_names[x] for x in labels))

	# Predict the model
	images = images.to(device)
	labels = images.to(device)
	output = model_resnet(images)

khalidmeister / save.model.py

Created June 23, 2020 14:55

Save the model

	# Save The Model
	PATH = './fix_alexnet_net.pth'
	torch.save(model_alexnet.state_dict(), PATH)

khalidmeister / load-model.py

Created June 23, 2020 14:57

Load the model

	# Declare the network
	net = Net()

	# Set the parameters
	net.load_state_dict(torch.load(PATH))

khalidmeister / app.py

Created June 24, 2020 07:06

The Main Process on A Web Application

	import io
	import string
	import torch
	import torch.nn as nn
	import torchvision.transforms as transforms
	from torchvision import models
	from flask import Flask, jsonify, request, render_template
	from PIL import Image

	app = Flask(__name__)

khalidmeister / layout.html

Created June 24, 2020 07:52

The template for our web page

	<!DOCTYPE HTML>
	<html>
	<head>
	<!-- Required meta tags -->
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">

	<!-- Bootstrap CSS -->
	<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.0/css/bootstrap.min.css" integrity="sha384-9aIt2nRpC12Uk9gS9baDl411NQApFmC26EwAOH8WgZl5MYYxFfc+NcPb1dKGj7Sk" crossorigin="anonymous">

khalidmeister / index.html

Created June 24, 2020 07:55

The Home Page

	{% extends "layout.html" %}
	{% block content %}
	<form class="form-signin" method=post enctype=multipart/form-data>
	<h1 class="h2 mb-3 font-weight-normal">Apple Leaf Disease Classifier</h1>
	<h2 class="h4 mb-3 font-weight-normal">Please Upload The Image</h2>
	<input type="file" name="file" class="form-control-file" id="inputfile" onchange="preview_image(event)">
	<br />
	<img id="output-image" class="rounded mx-auto d-block"/>
	<button class="btn btn-lg btn-primary btn-block" type="submit">Upload</button>
	<p class="mt-5 mb-3 text-muted">Powered by PyTorch, Flask, and Bootstrap.</p>

khalidmeister / result.html

Created June 24, 2020 07:56

Showing the result of our prediction

	{% extends "layout.html" %}
	{% block content %}
	<form class="form-signin" method=post enctype=multipart/form-data>
	{% if name == "healthy"%}
	<h1 class="h1 mb-3 font-weight-normal"> Your plant is healthy! </h1>
	{% else %}
	<h1 class="h1 mb-3 font-weight-normal"> Your leaf got a {{ name }} disease!</h5>
	<h3 class="h5 mb-3 font-weight-normal"> {{ description }} </p>
	{% endif %}
	<p class="mt-5 mb-3 text-muted">Powered by PyTorch, Flask, and Bootstrap.</p>

Irfan Alghani Khalid khalidmeister