2669 lines
589 KiB
Plaintext
2669 lines
589 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ab021475",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Jupyter notebook Lars Rook & Sem van der Hoeven"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ffa039c8",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Week 4"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "239c1156",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 4.1: ZTDL 1 - First Deep Learning Model\n",
|
||
"We hebben bij elk code blok comments gezet die uitleggen wat de code doet."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "155b55bd",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import numpy as np # import the numpy library and assign the name np to it\n",
|
||
"\n",
|
||
"# magic function that sets the backend of matplotlib to the inline backend\n",
|
||
"# source: https://stackoverflow.com/questions/43027980/purpose-of-matplotlib-inline\n",
|
||
"%matplotlib inline \n",
|
||
"import matplotlib.pyplot as plt # import the matplotlib.pyplot and assign the name plt to it"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "feeaffc8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.datasets import make_circles # import the make_circles module from the sklearn.datasets module"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c1db0180",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"roept de make_circles functie aan van de sklearn.datasets module\n",
|
||
"de make_circles functie maakt een cirkel met een kleinere cirkel hier binnen in.\n",
|
||
"- de n_samples staat voor hoeveel points gegenereerd moeten worden.\n",
|
||
"- de noise variabele staat voor hoeveel noise eraan toegeoegd moet worden\n",
|
||
"- de factor staat voor de schaling tussen de binnenste en buitenste cirkel\n",
|
||
"- de random_state variabele wordt gebruikt voor het genereren van een random nummer die gebruikt wordt voor het shufflen van de dataset en de noise.\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"X, y = make_circles(n_samples=1000,\n",
|
||
" noise=0.1,\n",
|
||
" factor=0.2,\n",
|
||
" random_state=0)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "46267e93",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# X bevat de gegenereerde samples van de make_circles methode.\n",
|
||
"\n",
|
||
"X"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "34c5864c",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# aangezien x de array of shape [n_samples, 2] bevat, geeft dit de gegeven aantal samples en 2.\n",
|
||
"X.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "fa762402",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier wordt met matplotlib een grafiek van de samples getekend.\n",
|
||
"allereerst wordt er een figuur aangemaakt, daarna worden de waarden die zijn gegenereerd getekend op deze figuur.\n",
|
||
"Hierna worden de limits van de x en y assen gezet.\n",
|
||
"Daarna wordt de legenda aangemaakt, hierbij zijn de bolletjes een 0 en de kruisjes een 1.\n",
|
||
"Als laatst wordt de titel van de figuur aangemaakt.\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"plt.figure(figsize=(5, 5))\n",
|
||
"plt.plot(X[y==0, 0], X[y==0, 1], 'ob', alpha=0.5)\n",
|
||
"plt.plot(X[y==1, 0], X[y==1, 1], 'xr', alpha=0.5)\n",
|
||
"plt.xlim(-1.5, 1.5)\n",
|
||
"plt.ylim(-1.5, 1.5)\n",
|
||
"plt.legend(['0', '1'])\n",
|
||
"plt.title(\"Blue circles and Red crosses\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9efb32c3",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# importeer modules van tensorflow\n",
|
||
"from tensorflow.keras.models import Sequential\n",
|
||
"from tensorflow.keras.layers import Dense\n",
|
||
"from tensorflow.keras.optimizers import SGD"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "43c0a1d3",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Maak een sequentieel model aan\n",
|
||
"model = Sequential()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "585aa0e2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# voeg een laag aan het model toe met 4 output neurons en 2 input neurons. Deze laag gebruikt de hyperbolic tangent activation functie.\n",
|
||
"model.add(Dense(4, input_shape=(2,), activation='tanh'))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "84e68325",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# voeg nog een laag toe met 1 output neuron. Deze laag gebruikt de Sigmoid activation function, sigmoid(x) = 1 / (1 + exp(-x))\n",
|
||
"model.add(Dense(1, activation='sigmoid'))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "fef8e12a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"compile configureert het model voor het trainen.\n",
|
||
"- als optimizer wordt de gradient descent optimizer gebruikt met een learning rate van 0.5\n",
|
||
"- als loss wordt binary cross entropy gebruikt. \n",
|
||
"- bij de metrics parameter wordt een lijst van attributen gezet waarop het model wordt geëvalueerd. In dit geval is het alleen de nauwkeurigheid\n",
|
||
"\"\"\" \n",
|
||
"model.compile(SGD(learning_rate=0.5), 'binary_crossentropy', metrics=['accuracy'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "0e1bcf7b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"fit traint het model voor het aantal gegeven epochs.\n",
|
||
"- X staat voor de input samples.\n",
|
||
"- y staat voor de target data (tensors)\n",
|
||
"- epochs staat voor hoe vaak het model getrained wordt.\n",
|
||
"\"\"\"\n",
|
||
"model.fit(X, y, epochs=20)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "20f9bb50",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"met de linspace functies worden nummers gegenereerd over een gelijk interval.\n",
|
||
"met de meshgrid functies worden coordinate matrices gemaakt van coordinate vectors.\n",
|
||
"met de c_ functie wordt een matrix gemaakt van de genenereerde arrays.\n",
|
||
"met de predict functie worden output predictions gegenereerd voor de input samples.\n",
|
||
"met de reshape functie wordt de shape aangepast naar die van de meshgrid.\n",
|
||
"\"\"\"\n",
|
||
"hticks = np.linspace(-1.5, 1.5, 101)\n",
|
||
"vticks = np.linspace(-1.5, 1.5, 101)\n",
|
||
"aa, bb = np.meshgrid(hticks, vticks)\n",
|
||
"ab = np.c_[aa.ravel(), bb.ravel()]\n",
|
||
"c = model.predict(ab)\n",
|
||
"cc = c.reshape(aa.shape)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a2e4f082",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"ab"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1e5b54db",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier wordt met matplotlib een grafiek van de samples getekend.\n",
|
||
"allereerst wordt er een figuur aangemaakt\n",
|
||
"Daarna wordt de contour getekend aan de hand van de output van het model.\n",
|
||
"Daarna worden de waarden die zijn gegenereerd getekend op deze figuur.\n",
|
||
"Hierna worden de limits van de x en y assen gezet.\n",
|
||
"Daarna wordt de legenda aangemaakt, hierbij zijn de bolletjes een 0 en de kruisjes een 1.\n",
|
||
"Als laatst wordt de titel van de figuur aangemaakt.\n",
|
||
"\"\"\"\n",
|
||
"plt.figure(figsize=(5, 5))\n",
|
||
"plt.contourf(aa, bb, cc, cmap='bwr', alpha=0.2)\n",
|
||
"plt.plot(X[y==0, 0], X[y==0, 1], 'ob', alpha=0.5)\n",
|
||
"plt.plot(X[y==1, 0], X[y==1, 1], 'xr', alpha=0.5)\n",
|
||
"plt.xlim(-1.5, 1.5)\n",
|
||
"plt.ylim(-1.5, 1.5)\n",
|
||
"plt.legend(['0', '1'])\n",
|
||
"plt.title(\"Blue circles and Red crosses\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9267f151",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 4.2 : ZTDL 2 - Data"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "20cea62e",
|
||
"metadata": {},
|
||
"source": [
|
||
"a. we hebben allebei het notebook bestudeerd.\n",
|
||
"b. we hebben een spreadsheet gevonden over heart attack analysis and predictions.\n",
|
||
"c. Hieronder zijn een aantal technieken en plots te zien die wij op de data hebben uitgevoerd. Om het beter te begrijpen hebben wij allebei samen de technieken en plots uitgevoerd."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "eaab705e",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Standaard info\n",
|
||
"We hebben eerst de standaard gegevens van de dataset verkend."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4deee696",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"%matplotlib inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6b792675",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = pd.read_csv('../data/heart.csv')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "81faf37f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"type(df)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6417b5c6",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "202237c5",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9a94370a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.describe()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "345b68bd",
|
||
"metadata": {},
|
||
"source": [
|
||
"### indexing\n",
|
||
"We zullen nu verschillende items in de dataset indexeren"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ce906842",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# het 10de element ophalen uit de dataset\n",
|
||
"df.iloc[10]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "5f8d9afe",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# de age, sex en oldpeak van de eerste 9 elementen ophalen\n",
|
||
"df.loc[0:8,['age','sex','oldpeak']]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ce4a5f85",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# de head opvragen van de elementen met het sex attribuut\n",
|
||
"df['sex'].head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d129b322",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# unieke element van sex ophalen\n",
|
||
"df['sex'].unique()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "37d36915",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# sorteer de values van attribuut age op optellende manier\n",
|
||
"df.sort_values('age', ascending = True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c379d785",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"dfplot = df[['age','chol']]\n",
|
||
"dfplot.plot(title='age chol relation')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "601da936",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"amountMale = df['sex'] > 0 # assuming male = 1\n",
|
||
"piecounts = amountMale.value_counts()\n",
|
||
"piecounts"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a128aabd",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"piecounts.plot(kind='pie',\n",
|
||
" figsize=(5, 5),\n",
|
||
" explode=[0, 0.12],\n",
|
||
" labels=['male', 'female'],\n",
|
||
" autopct='%1.1f%%',\n",
|
||
" shadow=True,\n",
|
||
" startangle=60,\n",
|
||
" fontsize=16);"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "95e144df",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 4.3 : ZTDL 3 – Machine Learning"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "79972227",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Linear regression\n",
|
||
"Deze code blokken zijn nodig als setup voor de linear regression met keras\n",
|
||
"We hebben gekozen voor een dataset die gebruikt kan worden voor linear regression. De dataset heeft geen bepaalde betekenis."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "09ee5be2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"%matplotlib inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "37389405",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# read the csv file into the df variable\n",
|
||
"df = pd.read_csv('../data/test.csv')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a7ea6eb2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# check out what is in the first few lines\n",
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "952802ba",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# plot the points in the dataset\n",
|
||
"df.plot(kind='scatter',\n",
|
||
" x='x',\n",
|
||
" y='y',\n",
|
||
" title='x and y in the dataset')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "8e9d0f89",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# plot the points again\n",
|
||
"df.plot(kind='scatter',\n",
|
||
" x='x',\n",
|
||
" y='y',\n",
|
||
" title='y and x in the data set')\n",
|
||
"\n",
|
||
"# Here we're plotting the red line 'by hand' with fixed values\n",
|
||
"# We'll try to learn this line with an algorithm below\n",
|
||
"plt.plot([55, 78], [75, 250], color='red', linewidth=3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "bf4cd5b6",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# define a method to calculate a point for a line given the input values\n",
|
||
"def line(x, w=0, b=0):\n",
|
||
" return x * w + b"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "b4842e99",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# generate evenly spaced numbers \n",
|
||
"x = np.linspace(55, 80, 100)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "479278e7",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"x"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "56cd60cd",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# generate line points\n",
|
||
"yhat = line(x, w=0, b=0)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "bd73d23f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"yhat"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7af98bd1",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# draw the points again, now with the line\n",
|
||
"df.plot(kind='scatter',\n",
|
||
" x='x',\n",
|
||
" y='y',\n",
|
||
" title='y en x in the data set')\n",
|
||
"plt.plot(x, yhat, color='red', linewidth=3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "077d7978",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Cost function"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "62838ac9",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# calculate the mean squared error given the input parameters.\n",
|
||
"def mean_squared_error(y_true, y_pred):\n",
|
||
" s = (y_true - y_pred)**2\n",
|
||
" return s.mean()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4bea9b4a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# get the x and y values from the dataset\n",
|
||
"X = df[['x']].values\n",
|
||
"y_true = df['y'].values"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "392f50b2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_true"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "0806d238",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# convert the points of the y values to line points\n",
|
||
"y_pred = line(X)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "aa0ef0f8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_pred"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "55ff0a77",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# calculate the mean square error for the points\n",
|
||
"mean_squared_error(y_true, y_pred.ravel())"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a60e5104",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Linear regression with keras"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ccde02ca",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from tensorflow.keras.models import Sequential\n",
|
||
"from tensorflow.keras.layers import Dense\n",
|
||
"from tensorflow.keras.optimizers import Adam, SGD"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "3c2b554a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"model = Sequential()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4da8d3b5",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# make a model with 1 layer, 1 output node and 1 input node\n",
|
||
"model.add(Dense(1, input_shape=(1,)))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "afbf17ff",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"model.summary()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "35dda627",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# get the model ready for training\n",
|
||
"model.compile(Adam(learning_rate=0.8), 'mean_squared_error')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "fe11b9d0",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# start training the model for 40 epochs\n",
|
||
"model.fit(X, y_true, epochs=40)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a22c9fb1",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_pred = model.predict(X)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9787ea0d",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.plot(kind='scatter',\n",
|
||
" x='x',\n",
|
||
" y='y',\n",
|
||
" title='x and y in the dataset, with prediction')\n",
|
||
"plt.plot(X, y_pred, color='red')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ccaf0068",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"W, B = model.get_weights()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "5e966641",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"W"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d7d8eb87",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"B"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "18ef5e31",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "bf431404",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Week 5"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "22d4d753",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Opdracht 5.1: ZTSL 4: Deep Learning Intro - shallow model"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7687f6bf",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Opdracht 5.1 b: We hebben een schets gemaakt van hoe wij denken dat het \n",
|
||
"model er uit zal zien. De code voor het inladen van de foto hebben wij \n",
|
||
"gehaald uit de practicumomschrijving.\n",
|
||
"\n",
|
||
"links zijn de I1 en I2 de inputs. De matrix van v11 en v12 stellen de \n",
|
||
"weegfactoren voor. In het midden is de sigmoid activatiefunctie te zien, en\n",
|
||
"rechts is de output te zien.\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"%pylab inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import matplotlib.image as mpimg\n",
|
||
"img = mpimg.imread('../data/opdr5-1-b.png')\n",
|
||
"plt.figure(figsize(20,10))\n",
|
||
"imgplot = plt.imshow(img)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e6979b5b",
|
||
"metadata": {},
|
||
"source": [
|
||
"Opdracht 5.1 c\n",
|
||
"Op basis van de hoeveelheid lagen, hebben wij geconcludeerd dat het shallow model niet genoeg lagen heeft om een accurate voorstelling te doen van een gegeven aantal inputs. Dit komt omdat het shallow model maar 1 hidden layer heeft."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "bf474d51",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Opdracht 5.2: ZTDL 4: Deep Learning Intro – deep model"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a8de57da",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Opdracht 5.2 b: We hebben een schets gemaakt van hoe wij denken dat het \n",
|
||
"model er uit zal zien. De code voor het inladen van de foto hebben wij \n",
|
||
"gehaald uit de practicumomschrijving.\n",
|
||
"\n",
|
||
"Er is te zien dat het model 2 inputs heeft, de eerste laag 4 outputs heeft, \n",
|
||
"de tweede laag 2 ouputs heeft en de 3e laag 1 output heeft. Ook is te zien\n",
|
||
"dat de eerste en 2e laag de tanh functie als activatiefunctie hebben, en de\n",
|
||
"derde laag de sigmoid functie als activatiefunctie gebruikt. De matrices met\n",
|
||
"de v, w en z waarden stellen de weegfactoren voor.\n",
|
||
"Dit netwerk heeft 3 lagen.\n",
|
||
"\n",
|
||
"(om de foto beter te zien is het aan te raden om in te zoomen)\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"%pylab inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import matplotlib.image as mpimg\n",
|
||
"img = mpimg.imread('../data/opdr5-2-b.png')\n",
|
||
"plt.figure(figsize(20,10))\n",
|
||
"imgplot = plt.imshow(img)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "f68cd874",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.2.c: De optimizer die wordt toegepast is de _binary crossentropy_ optimizer.\n",
|
||
"**wat is de functie van een optimizer:** De weegfactoren aanpassen zodat de loss function geminimaliseerd wordt. [Handige bron over optimizers](https://medium.datadriveninvestor.com/overview-of-different-optimizers-for-neural-networks-e0ed119440c3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "20230f3d",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.2.d: Uit de resultaten van de tests is te zien dat de accuracy van de trainingsset 0.999 (99.9%) is, en van de testset 1.000 (100%). Dit geeft aan dat het model heel goed is in het classificeren van de gevraagde features. De classificatie is dus erg goed."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6e60d43f",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.2.e: Hier is geen sprake van overfitting, aangezien de berekende lijn \n",
|
||
"(het witte gedeelte tussen de rode en blauwe delen) de scheiding volgt van de twee verschillende punten. Hierbij zitten er dus geen punten tussen die over deze scheiding zitten."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "331278a8",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Opdracht 5.3: ZTDL 4: Deep Learning Intro – Iris"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "85c1a69a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"%matplotlib inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import matplotlib.image as mpimg\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"from tensorflow.keras.models import Sequential\n",
|
||
"from tensorflow.keras.layers import Dense\n",
|
||
"from tensorflow.keras.optimizers import SGD, Adam\n",
|
||
"from sklearn.metrics import accuracy_score, confusion_matrix"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7b74afa5",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = pd.read_csv('../data/iris.csv')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "8da80225",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import seaborn as sns\n",
|
||
"sns.pairplot(df, hue=\"species\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6d64ebbd",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "e97352af",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"X = df.drop('species', axis=1)\n",
|
||
"X.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "bececaee",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"target_names = df['species'].unique()\n",
|
||
"target_names"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "89c4d761",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"target_dict = {n:i for i, n in enumerate(target_names)}\n",
|
||
"target_dict"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "19b2f7d4",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y= df['species'].map(target_dict)\n",
|
||
"y.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "16b5e400",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from tensorflow.keras.utils import to_categorical"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "b35398e4",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_cat = to_categorical(y)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6b41f15f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_cat[:10]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f7232f3c",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"X_train, X_test, y_train, y_test = train_test_split(X.values, y_cat,\n",
|
||
" test_size=0.2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "22fb3e06",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"model = Sequential()\n",
|
||
"model.add(Dense(3, input_shape=(4,), activation='softmax'))\n",
|
||
"model.compile(Adam(learning_rate=0.1),\n",
|
||
" loss='categorical_crossentropy',\n",
|
||
" metrics=['accuracy'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "da7f7f71",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"model.fit(X_train, y_train, epochs=20, validation_split=0.1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d84d95a0",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_pred = model.predict(X_test)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7dbaab2b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_pred[:5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "18656071",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"y_test_class = np.argmax(y_test, axis=1)\n",
|
||
"y_pred_class = np.argmax(y_pred, axis=1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "bba99886",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.metrics import classification_report"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9dcc6cc9",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"print(classification_report(y_test_class, y_pred_class))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "428f2066",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"confusion_matrix(y_test_class, y_pred_class)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4b279da6",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Opdracht 5.3 b: We hebben een schets gemaakt van hoe wij denken dat het \n",
|
||
"model er uit zal zien. De code voor het inladen van de foto hebben wij \n",
|
||
"gehaald uit de practicumomschrijving.\n",
|
||
"\n",
|
||
"Er is te zien dat dit netwerk maar 1 laag heeft, links zijn de inputs te \n",
|
||
"zien met rechts de activatie functies en de outputs.\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"img = mpimg.imread('../data/opdr5-3-b.png')\n",
|
||
"plt.figure(figsize(20,10))\n",
|
||
"imgplot = plt.imshow(img)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "4e57a19a",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.c: Hier wordt voor de softmax activation function gekozen omdat bij dit netwerk sprake is van meerdere klassen ('setosa', 'versicolor', 'virginica'). De softmax functie maakt het mogelijk om een multi-class vraagstuk op te lossen omdat het een decimale waarde geeft aan elke klasse, die representeert hoe veel het netwerk 'denkt' dat het die klasse is. De gegeven waarden aan de 3 resultaten (hoe veel het 'setosa', 'versicolor' of 'virginica' is) bij elkaar opgeteld is gelijk aan 1.0. [bron](https://developers.google.com/machine-learning/crash-course/multi-class-neural-networks/softmax)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0b2c6988",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.d: de learning rate geeft aan hoe snel het model leert. [bron](https://www.jeremyjordan.me/nn-learning-rate/).\n",
|
||
"we hebben de learning rate aangepast naar verschillende waarden en gekeken wat de loss en accuracy zijn. We hebben van elke learning rate de loss en accuracy van de laatste epoch opgenomen.\n",
|
||
"\n",
|
||
"\n",
|
||
"|learning rate |loss | accuracy|\n",
|
||
"--- | --- | ---\n",
|
||
"|0.1|0.2843|0.9815|\n",
|
||
"|0.5|0.1696|0.9259|\n",
|
||
"|0.8|0.1036|0.9630|\n",
|
||
"|1.0|0.1025|0.9537|\n",
|
||
"\n",
|
||
"\n",
|
||
"Uit deze verkregen waarden kunnen we concluderen dat een lagere learning rate zorgt voor een hogere accuracy maar ook een hogere loss. Hoe hoger de learning rate wordt, hoe minder updates worden uitgevoerd bij elke epoch, en worden de resultaten dus minder accuraat."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ccccde89",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.e: Er is hier geen sprake van overfitting. We kunnen doormiddel van te kijken naar de accuracy en loss bij elke epoch zien dat deze niet minder worden. Dit geeft aan dat er geen overfitting plaatsvindt. Ook kunnen we in de classification report zien dat het netwerk een accuracy van 0.97 heeft, wat ook aangeeft dat er geen overfitting plaatsvindt omdat dit hoog is."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "24bd3884",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.f: de _precision_ geeft aan hoe precies de voorstellen van het netwerk zijn , de positieve voorspelde uitkomsten. De _recall_ geeft aan hoeveel voorgestelde resultaten ook daadwerkelijk goed waren. De _f1 score_ geeft een gemiddelde aan van de precision en de recall. ([bron](https://wiki.pathmind.com/accuracy-precision-recall-f1))."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "aaad13a5",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.g: Uit de scores van het classification report kunnen we concluderen dat de betrouwbaaheid van het netwerk vrij hoog is, aangezien de waarden in het classification rapport vrij hoog zijn (niet lager dan 0.95)."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "85b233fb",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.h: uit de confusion matrix is te zien hoe vaak het netwerk een klasse van een bepaald type heeft geïdentificeerd terwijl dit een andere klasse is, ofwel hoe vaak het netwerk \"confused\" was ([bron](https://machinelearningmastery.com/confusion-matrix-machine-learning/))."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "f5922f60",
|
||
"metadata": {},
|
||
"source": [
|
||
"5.3.i: De informatie uit de confusion matrix is van belang bij het trekken van conclusies omdat hiermee duidelijk kan worden wat voor fouten het netwerk maakt."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e79ded8b",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Opdracht 5.4: Eenvoudig Classificatie vraagstuk"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "e4ff116f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"%matplotlib inline\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import matplotlib.image as mpimg\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"import seaborn as sns\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"from tensorflow.keras.models import Sequential\n",
|
||
"from tensorflow.keras.layers import Dense\n",
|
||
"from tensorflow.keras.optimizers import SGD, Adam\n",
|
||
"from sklearn.metrics import accuracy_score, confusion_matrix\n",
|
||
"from tensorflow.keras.utils import to_categorical\n",
|
||
"from sklearn.metrics import classification_report"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "60fdec44",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"leest de data uit van een .csv file.\n",
|
||
"\"\"\"\n",
|
||
"df = pd.read_csv('../data/Fish.csv')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "addf67b9",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<seaborn.axisgrid.PairGrid at 0x185ae515248>"
|
||
]
|
||
},
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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\n",
|
||
"text/plain": [
|
||
"<Figure size 1163.25x1080 with 42 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Plot voor elke verschillende soorten species elke attribute.\n",
|
||
"Zo zijn de soorten te zien in de kolommen en de attributen \n",
|
||
"zijn te zien in de rijen.\n",
|
||
"\"\"\"\n",
|
||
"sns.pairplot(df, hue=\"Species\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "5e9471b1",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Species</th>\n",
|
||
" <th>Weight</th>\n",
|
||
" <th>vLength</th>\n",
|
||
" <th>dLength</th>\n",
|
||
" <th>cLength</th>\n",
|
||
" <th>Height</th>\n",
|
||
" <th>Width</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>Bream</td>\n",
|
||
" <td>242.0</td>\n",
|
||
" <td>23.2</td>\n",
|
||
" <td>25.4</td>\n",
|
||
" <td>30.0</td>\n",
|
||
" <td>11.5200</td>\n",
|
||
" <td>4.0200</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>Bream</td>\n",
|
||
" <td>290.0</td>\n",
|
||
" <td>24.0</td>\n",
|
||
" <td>26.3</td>\n",
|
||
" <td>31.2</td>\n",
|
||
" <td>12.4800</td>\n",
|
||
" <td>4.3056</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Bream</td>\n",
|
||
" <td>340.0</td>\n",
|
||
" <td>23.9</td>\n",
|
||
" <td>26.5</td>\n",
|
||
" <td>31.1</td>\n",
|
||
" <td>12.3778</td>\n",
|
||
" <td>4.6961</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>Bream</td>\n",
|
||
" <td>363.0</td>\n",
|
||
" <td>26.3</td>\n",
|
||
" <td>29.0</td>\n",
|
||
" <td>33.5</td>\n",
|
||
" <td>12.7300</td>\n",
|
||
" <td>4.4555</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>Bream</td>\n",
|
||
" <td>430.0</td>\n",
|
||
" <td>26.5</td>\n",
|
||
" <td>29.0</td>\n",
|
||
" <td>34.0</td>\n",
|
||
" <td>12.4440</td>\n",
|
||
" <td>5.1340</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Species Weight vLength dLength cLength Height Width\n",
|
||
"0 Bream 242.0 23.2 25.4 30.0 11.5200 4.0200\n",
|
||
"1 Bream 290.0 24.0 26.3 31.2 12.4800 4.3056\n",
|
||
"2 Bream 340.0 23.9 26.5 31.1 12.3778 4.6961\n",
|
||
"3 Bream 363.0 26.3 29.0 33.5 12.7300 4.4555\n",
|
||
"4 Bream 430.0 26.5 29.0 34.0 12.4440 5.1340"
|
||
]
|
||
},
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Laat de eerste aantal waardes van de dataset zien.\n",
|
||
"vLength:verticale lengte van de vis.\n",
|
||
"dLength: diagonale lengte van de vis.\n",
|
||
"clength: kruisende lengte van de vis.\n",
|
||
"\"\"\"\n",
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "6f7b95c2",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Weight</th>\n",
|
||
" <th>vLength</th>\n",
|
||
" <th>dLength</th>\n",
|
||
" <th>cLength</th>\n",
|
||
" <th>Height</th>\n",
|
||
" <th>Width</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>242.0</td>\n",
|
||
" <td>23.2</td>\n",
|
||
" <td>25.4</td>\n",
|
||
" <td>30.0</td>\n",
|
||
" <td>11.5200</td>\n",
|
||
" <td>4.0200</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>290.0</td>\n",
|
||
" <td>24.0</td>\n",
|
||
" <td>26.3</td>\n",
|
||
" <td>31.2</td>\n",
|
||
" <td>12.4800</td>\n",
|
||
" <td>4.3056</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>340.0</td>\n",
|
||
" <td>23.9</td>\n",
|
||
" <td>26.5</td>\n",
|
||
" <td>31.1</td>\n",
|
||
" <td>12.3778</td>\n",
|
||
" <td>4.6961</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>363.0</td>\n",
|
||
" <td>26.3</td>\n",
|
||
" <td>29.0</td>\n",
|
||
" <td>33.5</td>\n",
|
||
" <td>12.7300</td>\n",
|
||
" <td>4.4555</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>430.0</td>\n",
|
||
" <td>26.5</td>\n",
|
||
" <td>29.0</td>\n",
|
||
" <td>34.0</td>\n",
|
||
" <td>12.4440</td>\n",
|
||
" <td>5.1340</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Weight vLength dLength cLength Height Width\n",
|
||
"0 242.0 23.2 25.4 30.0 11.5200 4.0200\n",
|
||
"1 290.0 24.0 26.3 31.2 12.4800 4.3056\n",
|
||
"2 340.0 23.9 26.5 31.1 12.3778 4.6961\n",
|
||
"3 363.0 26.3 29.0 33.5 12.7300 4.4555\n",
|
||
"4 430.0 26.5 29.0 34.0 12.4440 5.1340"
|
||
]
|
||
},
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Haal de species kolom uit de originele dataset zodat \n",
|
||
"alleen de attributen overblijven.\n",
|
||
"Axis=1 -> alleen de kolom weghalen.\n",
|
||
"\"\"\"\n",
|
||
"X = df.drop('Species', axis=1)\n",
|
||
"X.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "67a3c7e8",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array(['Bream', 'Roach', 'Whitefish', 'Parkki', 'Perch', 'Pike', 'Smelt'],\n",
|
||
" dtype=object)"
|
||
]
|
||
},
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Kijken wat alle target names zijn, oftewel\n",
|
||
"kijken wat voor vissoorten er zijn. \n",
|
||
"\"\"\"\n",
|
||
"target_names = df['Species'].unique()\n",
|
||
"target_names"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "a15e9228",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"{'Bream': 0,\n",
|
||
" 'Roach': 1,\n",
|
||
" 'Whitefish': 2,\n",
|
||
" 'Parkki': 3,\n",
|
||
" 'Perch': 4,\n",
|
||
" 'Pike': 5,\n",
|
||
" 'Smelt': 6}"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Zet de verschillende vissoorten om in een enum,\n",
|
||
"zodat er gewerkt kan worden met cijfers i.p.v. namen.\n",
|
||
"\"\"\"\n",
|
||
"target_dict = {n:i for i, n in enumerate(target_names)}\n",
|
||
"target_dict"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "13665adc",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0 0\n",
|
||
"1 0\n",
|
||
"2 0\n",
|
||
"3 0\n",
|
||
"4 0\n",
|
||
"Name: Species, dtype: int64"
|
||
]
|
||
},
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"map de namen naar getal waardes uit de enum.\n",
|
||
"Hier is te zien dat de eerste aantal waardes Breams zijn,\n",
|
||
"want deze hebben de waarde 0.\n",
|
||
"\"\"\"\n",
|
||
"y= df['Species'].map(target_dict)\n",
|
||
"y.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "300338ad",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Zet het om naar een binaire matrix die aangeeft welke \n",
|
||
"categorie vis het is.\n",
|
||
"\"\"\"\n",
|
||
"y_cat = to_categorical(y)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "d28b268c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.],\n",
|
||
" [1., 0., 0., 0., 0., 0., 0.]], dtype=float32)"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"y_cat[:10]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"id": "ca140c57",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"split de originele dataset naar training en test waardes.\n",
|
||
"De size van de testwaardes is 20% van het originele.\n",
|
||
"\"\"\"\n",
|
||
"X_train, X_test, y_train, y_test = train_test_split(X.values, y_cat,\n",
|
||
" test_size=0.2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 28,
|
||
"id": "d7dfed0b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Maak een sequentieel model met 1 hidden layer die \n",
|
||
"7 outputs en 6 inputs heeft. We gebruiken softmax als \n",
|
||
"activation function, omdat we gebruik maken van verschillende\n",
|
||
"categorieen vissen. \n",
|
||
"Verder is er een learning_rate van 0.1, omdat na het testen\n",
|
||
"wij er achter kwamen dat dit het beste resultaat was.\n",
|
||
"Als loss gebruiken we categorical_crossentropy, omdat we \n",
|
||
"gebruik maken van meer dan twee klassen\n",
|
||
"(in dit geval, verschillende vissen) die gerepresenteerd \n",
|
||
"worden door getallen. En gebruiken als metrics accuracy, \n",
|
||
"zodat we de nauwkeurigheid kunnen zien.\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"model = Sequential()\n",
|
||
"model.add(Dense(7, input_shape=(6,), activation='softmax'))\n",
|
||
"model.compile(Adam(learning_rate=0.1),\n",
|
||
" loss='categorical_crossentropy',\n",
|
||
" metrics=['accuracy'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 84,
|
||
"id": "c0f03c94",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Epoch 1/200\n",
|
||
"3/3 [==============================] - 0s 17ms/step - loss: 0.5206 - accuracy: 0.9773 - val_loss: 0.0036 - val_accuracy: 1.0000\n",
|
||
"Epoch 2/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0247 - accuracy: 0.9773 - val_loss: 0.0759 - val_accuracy: 0.9744\n",
|
||
"Epoch 3/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.0789 - accuracy: 0.9545 - val_loss: 0.2719 - val_accuracy: 0.9744\n",
|
||
"Epoch 4/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3323 - accuracy: 0.9773 - val_loss: 0.2406 - val_accuracy: 0.9744\n",
|
||
"Epoch 5/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.2357 - accuracy: 0.9773 - val_loss: 0.0148 - val_accuracy: 1.0000\n",
|
||
"Epoch 6/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2188 - accuracy: 0.9545 - val_loss: 0.0462 - val_accuracy: 0.9744\n",
|
||
"Epoch 7/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8885 - accuracy: 0.9432 - val_loss: 0.2280 - val_accuracy: 0.9487\n",
|
||
"Epoch 8/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5118 - accuracy: 0.9773 - val_loss: 0.0670 - val_accuracy: 0.9744\n",
|
||
"Epoch 9/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1492 - accuracy: 0.9545 - val_loss: 0.0689 - val_accuracy: 0.9744\n",
|
||
"Epoch 10/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0412 - accuracy: 0.9773 - val_loss: 0.0060 - val_accuracy: 1.0000\n",
|
||
"Epoch 11/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0834 - accuracy: 0.9659 - val_loss: 0.0057 - val_accuracy: 1.0000\n",
|
||
"Epoch 12/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0250 - accuracy: 0.9886 - val_loss: 0.0281 - val_accuracy: 0.9744\n",
|
||
"Epoch 13/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.0404 - accuracy: 0.9886 - val_loss: 0.0184 - val_accuracy: 1.0000\n",
|
||
"Epoch 14/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0251 - accuracy: 0.9886 - val_loss: 0.0078 - val_accuracy: 1.0000\n",
|
||
"Epoch 15/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0266 - accuracy: 0.9886 - val_loss: 0.0090 - val_accuracy: 1.0000\n",
|
||
"Epoch 16/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0990 - accuracy: 0.9773 - val_loss: 0.0191 - val_accuracy: 1.0000\n",
|
||
"Epoch 17/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0637 - accuracy: 0.9773 - val_loss: 0.0672 - val_accuracy: 0.9744\n",
|
||
"Epoch 18/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0860 - accuracy: 0.9659 - val_loss: 0.2937 - val_accuracy: 0.9487\n",
|
||
"Epoch 19/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3007 - accuracy: 0.9659 - val_loss: 0.1315 - val_accuracy: 0.9744\n",
|
||
"Epoch 20/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1904 - accuracy: 0.9659 - val_loss: 0.0435 - val_accuracy: 1.0000\n",
|
||
"Epoch 21/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3595 - accuracy: 0.9432 - val_loss: 0.0273 - val_accuracy: 1.0000\n",
|
||
"Epoch 22/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0295 - accuracy: 0.9886 - val_loss: 0.0670 - val_accuracy: 0.9744\n",
|
||
"Epoch 23/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2149 - accuracy: 0.9659 - val_loss: 0.2545 - val_accuracy: 0.9744\n",
|
||
"Epoch 24/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3584 - accuracy: 0.9773 - val_loss: 0.4169 - val_accuracy: 0.9744\n",
|
||
"Epoch 25/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5446 - accuracy: 0.9773 - val_loss: 0.1386 - val_accuracy: 0.9744\n",
|
||
"Epoch 26/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.0227 - accuracy: 0.9886 - val_loss: 0.3672 - val_accuracy: 0.8718\n",
|
||
"Epoch 27/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.6265 - accuracy: 0.8750 - val_loss: 0.0944 - val_accuracy: 0.9744\n",
|
||
"Epoch 28/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4360 - accuracy: 0.9773 - val_loss: 0.8519 - val_accuracy: 0.9487\n",
|
||
"Epoch 29/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 1.0507 - accuracy: 0.9659 - val_loss: 0.6263 - val_accuracy: 0.9744\n",
|
||
"Epoch 30/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8534 - accuracy: 0.9773 - val_loss: 0.1176 - val_accuracy: 0.9744\n",
|
||
"Epoch 31/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1868 - accuracy: 0.9659 - val_loss: 1.9173 - val_accuracy: 0.8205\n",
|
||
"Epoch 32/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.7339 - accuracy: 0.8636 - val_loss: 0.5966 - val_accuracy: 0.9487\n",
|
||
"Epoch 33/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.3977 - accuracy: 0.9545 - val_loss: 1.0357 - val_accuracy: 0.9744\n",
|
||
"Epoch 34/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.9053 - accuracy: 0.9659 - val_loss: 1.4874 - val_accuracy: 0.8974\n",
|
||
"Epoch 35/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.7001 - accuracy: 0.9432 - val_loss: 0.8853 - val_accuracy: 0.9487\n",
|
||
"Epoch 36/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.9437 - accuracy: 0.9659 - val_loss: 0.0354 - val_accuracy: 0.9744\n",
|
||
"Epoch 37/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0500 - accuracy: 0.9886 - val_loss: 0.0990 - val_accuracy: 0.9487\n",
|
||
"Epoch 38/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5018 - accuracy: 0.9545 - val_loss: 0.0912 - val_accuracy: 0.9744\n",
|
||
"Epoch 39/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7885 - accuracy: 0.9545 - val_loss: 0.4366 - val_accuracy: 0.9744\n",
|
||
"Epoch 40/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.6568 - accuracy: 0.9773 - val_loss: 0.5445 - val_accuracy: 0.8974\n",
|
||
"Epoch 41/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.4604 - accuracy: 0.9432 - val_loss: 0.1088 - val_accuracy: 0.9744\n",
|
||
"Epoch 42/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0234 - accuracy: 0.9886 - val_loss: 0.0079 - val_accuracy: 1.0000\n",
|
||
"Epoch 43/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1765 - accuracy: 0.9773 - val_loss: 0.0175 - val_accuracy: 1.0000\n",
|
||
"Epoch 44/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0640 - accuracy: 0.9773 - val_loss: 0.0388 - val_accuracy: 0.9744\n",
|
||
"Epoch 45/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.2965 - accuracy: 0.9545 - val_loss: 0.2530 - val_accuracy: 0.9744\n",
|
||
"Epoch 46/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2401 - accuracy: 0.9773 - val_loss: 0.3233 - val_accuracy: 0.9487\n",
|
||
"Epoch 47/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.6475 - accuracy: 0.9659 - val_loss: 0.1328 - val_accuracy: 0.9487\n",
|
||
"Epoch 48/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4413 - accuracy: 0.9318 - val_loss: 0.0080 - val_accuracy: 1.0000\n",
|
||
"Epoch 49/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1479 - accuracy: 0.9659 - val_loss: 0.4669 - val_accuracy: 0.9231\n",
|
||
"Epoch 50/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.6728 - accuracy: 0.9545 - val_loss: 0.3281 - val_accuracy: 0.9744\n",
|
||
"Epoch 51/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2909 - accuracy: 0.9773 - val_loss: 0.0382 - val_accuracy: 1.0000\n",
|
||
"Epoch 52/200\n",
|
||
"3/3 [==============================] - 0s 9ms/step - loss: 0.1910 - accuracy: 0.9659 - val_loss: 0.0072 - val_accuracy: 1.0000\n",
|
||
"Epoch 53/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0068 - accuracy: 1.0000 - val_loss: 0.1226 - val_accuracy: 0.9744\n",
|
||
"Epoch 54/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1400 - accuracy: 0.9773 - val_loss: 0.0442 - val_accuracy: 0.9744\n",
|
||
"Epoch 55/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1295 - accuracy: 0.9659 - val_loss: 0.0060 - val_accuracy: 1.0000\n",
|
||
"Epoch 56/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0178 - accuracy: 0.9886 - val_loss: 0.0170 - val_accuracy: 1.0000\n",
|
||
"Epoch 57/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1287 - accuracy: 0.9773 - val_loss: 0.1429 - val_accuracy: 0.9744\n",
|
||
"Epoch 58/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7361 - accuracy: 0.9773 - val_loss: 0.3757 - val_accuracy: 0.9744\n",
|
||
"Epoch 59/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5845 - accuracy: 0.9773 - val_loss: 0.0177 - val_accuracy: 1.0000\n",
|
||
"Epoch 60/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2937 - accuracy: 0.9545 - val_loss: 0.0459 - val_accuracy: 0.9744\n",
|
||
"Epoch 61/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.6923 - accuracy: 0.9545 - val_loss: 0.4607 - val_accuracy: 0.9487\n",
|
||
"Epoch 62/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.3217 - accuracy: 0.9545 - val_loss: 0.6247 - val_accuracy: 0.9744\n",
|
||
"Epoch 63/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 1.0299 - accuracy: 0.9659 - val_loss: 0.4073 - val_accuracy: 0.9231\n",
|
||
"Epoch 64/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3026 - accuracy: 0.9545 - val_loss: 0.1440 - val_accuracy: 0.9231\n",
|
||
"Epoch 65/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2659 - accuracy: 0.9545 - val_loss: 0.0408 - val_accuracy: 1.0000\n",
|
||
"Epoch 66/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4159 - accuracy: 0.9545 - val_loss: 0.0206 - val_accuracy: 1.0000\n",
|
||
"Epoch 67/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0796 - accuracy: 0.9659 - val_loss: 0.0811 - val_accuracy: 0.9487\n",
|
||
"Epoch 68/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1921 - accuracy: 0.9659 - val_loss: 0.0950 - val_accuracy: 0.9744\n",
|
||
"Epoch 69/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4226 - accuracy: 0.8977 - val_loss: 0.0113 - val_accuracy: 1.0000\n",
|
||
"Epoch 70/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.7923 - accuracy: 0.9659 - val_loss: 0.4664 - val_accuracy: 0.9744\n",
|
||
"Epoch 71/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.9960 - accuracy: 0.9773 - val_loss: 0.3829 - val_accuracy: 0.9744\n",
|
||
"Epoch 72/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.7189 - accuracy: 0.9773 - val_loss: 0.0108 - val_accuracy: 1.0000\n",
|
||
"Epoch 73/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7764 - accuracy: 0.9091 - val_loss: 0.4123 - val_accuracy: 0.9744\n",
|
||
"Epoch 74/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8827 - accuracy: 0.9545 - val_loss: 0.7937 - val_accuracy: 0.9487\n",
|
||
"Epoch 75/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.6369 - accuracy: 0.9545 - val_loss: 0.9508 - val_accuracy: 0.9744\n",
|
||
"Epoch 76/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.4822 - accuracy: 0.9659 - val_loss: 0.9712 - val_accuracy: 0.8974\n",
|
||
"Epoch 77/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.9156 - accuracy: 0.9318 - val_loss: 0.0563 - val_accuracy: 0.9744\n",
|
||
"Epoch 78/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.0907 - accuracy: 0.8977 - val_loss: 0.4499 - val_accuracy: 0.9231\n",
|
||
"Epoch 79/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.8759 - accuracy: 0.9205 - val_loss: 0.3217 - val_accuracy: 0.9744\n",
|
||
"Epoch 80/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4840 - accuracy: 0.9773 - val_loss: 1.6545 - val_accuracy: 0.7692\n",
|
||
"Epoch 81/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.6836 - accuracy: 0.9091 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
|
||
"Epoch 82/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.2093 - accuracy: 0.9659 - val_loss: 0.0944 - val_accuracy: 0.9744\n",
|
||
"Epoch 83/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5031 - accuracy: 0.9659 - val_loss: 0.0097 - val_accuracy: 1.0000\n",
|
||
"Epoch 84/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3053 - accuracy: 0.9545 - val_loss: 0.4800 - val_accuracy: 0.9487\n",
|
||
"Epoch 85/200\n",
|
||
"3/3 [==============================] - ETA: 0s - loss: 0.2510 - accuracy: 0.96 - 0s 7ms/step - loss: 0.6734 - accuracy: 0.9318 - val_loss: 0.9602 - val_accuracy: 0.8462\n",
|
||
"Epoch 86/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7874 - accuracy: 0.9205 - val_loss: 0.1413 - val_accuracy: 0.9487\n",
|
||
"Epoch 87/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.9946 - accuracy: 0.9318 - val_loss: 1.0971 - val_accuracy: 0.8974\n",
|
||
"Epoch 88/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 2.0151 - accuracy: 0.9091 - val_loss: 0.8202 - val_accuracy: 0.9744\n",
|
||
"Epoch 89/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.4868 - accuracy: 0.9432 - val_loss: 1.9732 - val_accuracy: 0.7692\n",
|
||
"Epoch 90/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7131 - accuracy: 0.9091 - val_loss: 0.2275 - val_accuracy: 0.9744\n",
|
||
"Epoch 91/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.4174 - accuracy: 0.8750 - val_loss: 0.6450 - val_accuracy: 0.9231\n",
|
||
"Epoch 92/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.3239 - accuracy: 0.8864 - val_loss: 0.0036 - val_accuracy: 1.0000\n",
|
||
"Epoch 93/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5266 - accuracy: 0.9205 - val_loss: 2.1191 - val_accuracy: 0.7436\n",
|
||
"Epoch 94/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.9957 - accuracy: 0.8523 - val_loss: 0.0514 - val_accuracy: 0.9744\n",
|
||
"Epoch 95/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1648 - accuracy: 0.9773 - val_loss: 0.2579 - val_accuracy: 0.9487\n",
|
||
"Epoch 96/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.2900 - accuracy: 0.8864 - val_loss: 0.7580 - val_accuracy: 0.9231\n",
|
||
"Epoch 97/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 2.4941 - accuracy: 0.9318 - val_loss: 1.2591 - val_accuracy: 0.9744\n",
|
||
"Epoch 98/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 2.5769 - accuracy: 0.9205 - val_loss: 2.7963 - val_accuracy: 0.7949\n",
|
||
"Epoch 99/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 2.2847 - accuracy: 0.8636 - val_loss: 0.9382 - val_accuracy: 0.9744\n",
|
||
"Epoch 100/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.3325 - accuracy: 0.9773 - val_loss: 0.1524 - val_accuracy: 0.9744\n",
|
||
"Epoch 101/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.9787 - accuracy: 0.8750 - val_loss: 0.2437 - val_accuracy: 0.9744\n",
|
||
"Epoch 102/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.6337 - accuracy: 0.9318 - val_loss: 0.5005 - val_accuracy: 0.9744\n",
|
||
"Epoch 103/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.7674 - accuracy: 0.9545 - val_loss: 1.3002 - val_accuracy: 0.8718\n",
|
||
"Epoch 104/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.6001 - accuracy: 0.9318 - val_loss: 0.0499 - val_accuracy: 0.9487\n",
|
||
"Epoch 105/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8319 - accuracy: 0.9205 - val_loss: 0.4269 - val_accuracy: 0.9231\n",
|
||
"Epoch 106/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7168 - accuracy: 0.9205 - val_loss: 0.0114 - val_accuracy: 1.0000\n",
|
||
"Epoch 107/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1257 - accuracy: 0.9886 - val_loss: 0.6496 - val_accuracy: 0.8974\n",
|
||
"Epoch 108/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4558 - accuracy: 0.9318 - val_loss: 0.3380 - val_accuracy: 0.9487\n",
|
||
"Epoch 109/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1925 - accuracy: 0.9432 - val_loss: 0.0739 - val_accuracy: 0.9744\n",
|
||
"Epoch 110/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3303 - accuracy: 0.9432 - val_loss: 0.0239 - val_accuracy: 0.9744\n",
|
||
"Epoch 111/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1337 - accuracy: 0.9773 - val_loss: 0.1382 - val_accuracy: 0.9744\n",
|
||
"Epoch 112/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1967 - accuracy: 0.9773 - val_loss: 0.2847 - val_accuracy: 0.9744\n",
|
||
"Epoch 113/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3294 - accuracy: 0.9773 - val_loss: 0.0261 - val_accuracy: 0.9744\n",
|
||
"Epoch 114/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2683 - accuracy: 0.9545 - val_loss: 0.0026 - val_accuracy: 1.0000\n",
|
||
"Epoch 115/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0619 - accuracy: 0.9773 - val_loss: 0.0997 - val_accuracy: 0.9744\n",
|
||
"Epoch 116/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1355 - accuracy: 0.9773 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
|
||
"Epoch 117/200\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.3234 - accuracy: 0.9545 - val_loss: 0.0961 - val_accuracy: 0.9744\n",
|
||
"Epoch 118/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4853 - accuracy: 0.9773 - val_loss: 0.2908 - val_accuracy: 0.9744\n",
|
||
"Epoch 119/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.4906 - accuracy: 0.9773 - val_loss: 0.0257 - val_accuracy: 0.9744\n",
|
||
"Epoch 120/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3162 - accuracy: 0.9659 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
|
||
"Epoch 121/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2849 - accuracy: 0.9659 - val_loss: 0.0979 - val_accuracy: 0.9744\n",
|
||
"Epoch 122/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3187 - accuracy: 0.9773 - val_loss: 0.0033 - val_accuracy: 1.0000\n",
|
||
"Epoch 123/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1126 - accuracy: 0.9773 - val_loss: 0.1149 - val_accuracy: 0.9231\n",
|
||
"Epoch 124/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1051 - accuracy: 0.9432 - val_loss: 0.2839 - val_accuracy: 0.9744\n",
|
||
"Epoch 125/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.0049 - accuracy: 0.9773 - val_loss: 0.4689 - val_accuracy: 0.9487\n",
|
||
"Epoch 126/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.1950 - accuracy: 0.9545 - val_loss: 0.2502 - val_accuracy: 0.9744\n",
|
||
"Epoch 127/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1796 - accuracy: 0.9773 - val_loss: 0.4300 - val_accuracy: 0.8974\n",
|
||
"Epoch 128/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3250 - accuracy: 0.9545 - val_loss: 0.0942 - val_accuracy: 0.9744\n",
|
||
"Epoch 129/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2772 - accuracy: 0.9773 - val_loss: 0.0094 - val_accuracy: 1.0000\n",
|
||
"Epoch 130/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2034 - accuracy: 0.9659 - val_loss: 0.0181 - val_accuracy: 1.0000\n",
|
||
"Epoch 131/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0882 - accuracy: 0.9659 - val_loss: 0.4715 - val_accuracy: 0.8974\n",
|
||
"Epoch 132/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2472 - accuracy: 0.9432 - val_loss: 0.2285 - val_accuracy: 0.9744\n",
|
||
"Epoch 133/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.6401 - accuracy: 0.9773 - val_loss: 0.2137 - val_accuracy: 0.9487\n",
|
||
"Epoch 134/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7154 - accuracy: 0.9545 - val_loss: 0.0188 - val_accuracy: 1.0000\n",
|
||
"Epoch 135/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0553 - accuracy: 0.9886 - val_loss: 0.3086 - val_accuracy: 0.9231\n",
|
||
"Epoch 136/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1487 - accuracy: 0.9318 - val_loss: 0.2052 - val_accuracy: 0.9744\n",
|
||
"Epoch 137/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2273 - accuracy: 0.9773 - val_loss: 0.0711 - val_accuracy: 0.9744\n",
|
||
"Epoch 138/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2857 - accuracy: 0.9545 - val_loss: 0.0286 - val_accuracy: 1.0000\n",
|
||
"Epoch 139/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4483 - accuracy: 0.9659 - val_loss: 0.4201 - val_accuracy: 0.9744\n",
|
||
"Epoch 140/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.1021 - accuracy: 0.9773 - val_loss: 0.5995 - val_accuracy: 0.9744\n",
|
||
"Epoch 141/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.7406 - accuracy: 0.9773 - val_loss: 0.1149 - val_accuracy: 0.9744\n",
|
||
"Epoch 142/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3356 - accuracy: 0.9659 - val_loss: 0.0205 - val_accuracy: 1.0000\n",
|
||
"Epoch 143/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0521 - accuracy: 0.9773 - val_loss: 0.0586 - val_accuracy: 0.9744\n",
|
||
"Epoch 144/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1695 - accuracy: 0.9659 - val_loss: 0.0394 - val_accuracy: 0.9744\n",
|
||
"Epoch 145/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1547 - accuracy: 0.9545 - val_loss: 0.2377 - val_accuracy: 0.9744\n",
|
||
"Epoch 146/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3077 - accuracy: 0.9773 - val_loss: 0.4282 - val_accuracy: 0.9744\n",
|
||
"Epoch 147/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.0188 - accuracy: 0.9659 - val_loss: 0.3589 - val_accuracy: 0.9744\n",
|
||
"Epoch 148/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8012 - accuracy: 0.9773 - val_loss: 0.1308 - val_accuracy: 0.9487\n",
|
||
"Epoch 149/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.2854 - accuracy: 0.8523 - val_loss: 0.8737 - val_accuracy: 0.9487\n",
|
||
"Epoch 150/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 2.1476 - accuracy: 0.9205 - val_loss: 1.8352 - val_accuracy: 0.9487\n",
|
||
"Epoch 151/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 3.8552 - accuracy: 0.9545 - val_loss: 2.4989 - val_accuracy: 0.9744\n",
|
||
"Epoch 152/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 4.4399 - accuracy: 0.9318 - val_loss: 2.9586 - val_accuracy: 0.8718\n",
|
||
"Epoch 153/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 3.6093 - accuracy: 0.9318 - val_loss: 1.5124 - val_accuracy: 0.9744\n",
|
||
"Epoch 154/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 2.6838 - accuracy: 0.9432 - val_loss: 0.6747 - val_accuracy: 0.9487\n",
|
||
"Epoch 155/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.6222 - accuracy: 0.9773 - val_loss: 0.3497 - val_accuracy: 0.8974\n",
|
||
"Epoch 156/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 1.4076 - accuracy: 0.8295 - val_loss: 0.2433 - val_accuracy: 0.9487\n",
|
||
"Epoch 157/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.7072 - accuracy: 0.9659 - val_loss: 0.5289 - val_accuracy: 0.9744\n",
|
||
"Epoch 158/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.2567 - accuracy: 0.9659 - val_loss: 0.5061 - val_accuracy: 0.9744\n",
|
||
"Epoch 159/200\n",
|
||
"3/3 [==============================] - 0s 9ms/step - loss: 0.8594 - accuracy: 0.9773 - val_loss: 0.2794 - val_accuracy: 0.9487\n",
|
||
"Epoch 160/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7753 - accuracy: 0.9091 - val_loss: 0.0923 - val_accuracy: 0.9744\n",
|
||
"Epoch 161/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.4531 - accuracy: 0.9545 - val_loss: 1.2632 - val_accuracy: 0.8974\n",
|
||
"Epoch 162/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 2.4088 - accuracy: 0.9091 - val_loss: 0.7960 - val_accuracy: 0.9744\n",
|
||
"Epoch 163/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 1.6359 - accuracy: 0.9545 - val_loss: 1.0379 - val_accuracy: 0.8718\n",
|
||
"Epoch 164/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.9048 - accuracy: 0.9318 - val_loss: 0.1933 - val_accuracy: 0.9231\n",
|
||
"Epoch 165/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7675 - accuracy: 0.8977 - val_loss: 0.0129 - val_accuracy: 1.0000\n",
|
||
"Epoch 166/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.4277 - accuracy: 0.9659 - val_loss: 0.1332 - val_accuracy: 0.9744\n",
|
||
"Epoch 167/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3905 - accuracy: 0.9432 - val_loss: 0.0726 - val_accuracy: 0.9487\n",
|
||
"Epoch 168/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1751 - accuracy: 0.9659 - val_loss: 0.0112 - val_accuracy: 1.0000\n",
|
||
"Epoch 169/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1781 - accuracy: 0.9659 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
|
||
"Epoch 170/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0481 - accuracy: 0.9886 - val_loss: 0.1648 - val_accuracy: 0.9744\n",
|
||
"Epoch 171/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2228 - accuracy: 0.9773 - val_loss: 0.2157 - val_accuracy: 0.9487\n",
|
||
"Epoch 172/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.1360 - accuracy: 0.9773 - val_loss: 0.0234 - val_accuracy: 1.0000\n",
|
||
"Epoch 173/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1469 - accuracy: 0.9659 - val_loss: 0.0264 - val_accuracy: 0.9744\n",
|
||
"Epoch 174/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.4156 - accuracy: 0.9659 - val_loss: 0.1467 - val_accuracy: 0.9744\n",
|
||
"Epoch 175/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3312 - accuracy: 0.9659 - val_loss: 0.0123 - val_accuracy: 1.0000\n",
|
||
"Epoch 176/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1016 - accuracy: 0.9659 - val_loss: 0.0146 - val_accuracy: 1.0000\n",
|
||
"Epoch 177/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0888 - accuracy: 0.9886 - val_loss: 0.2364 - val_accuracy: 0.9744\n",
|
||
"Epoch 178/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4399 - accuracy: 0.9773 - val_loss: 0.0469 - val_accuracy: 0.9744\n",
|
||
"Epoch 179/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1174 - accuracy: 0.9773 - val_loss: 0.0050 - val_accuracy: 1.0000\n",
|
||
"Epoch 180/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.1204 - accuracy: 0.9659 - val_loss: 0.0557 - val_accuracy: 0.9744\n",
|
||
"Epoch 181/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0776 - accuracy: 0.9886 - val_loss: 0.0269 - val_accuracy: 0.9744\n",
|
||
"Epoch 182/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0889 - accuracy: 0.9886 - val_loss: 0.0074 - val_accuracy: 1.0000\n",
|
||
"Epoch 183/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.4608 - accuracy: 0.9545 - val_loss: 0.0300 - val_accuracy: 0.9744\n",
|
||
"Epoch 184/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3956 - accuracy: 0.9318 - val_loss: 0.1729 - val_accuracy: 0.9487\n",
|
||
"Epoch 185/200\n",
|
||
"3/3 [==============================] - 0s 6ms/step - loss: 0.1932 - accuracy: 0.9659 - val_loss: 0.7135 - val_accuracy: 0.9744\n",
|
||
"Epoch 186/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.7701 - accuracy: 0.9773 - val_loss: 1.0560 - val_accuracy: 0.9744\n",
|
||
"Epoch 187/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.8375 - accuracy: 0.9773 - val_loss: 0.7653 - val_accuracy: 0.9744\n",
|
||
"Epoch 188/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.1190 - accuracy: 0.9773 - val_loss: 0.2145 - val_accuracy: 0.9744\n",
|
||
"Epoch 189/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.1489 - accuracy: 0.9659 - val_loss: 0.5175 - val_accuracy: 0.8205\n",
|
||
"Epoch 190/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.3515 - accuracy: 0.9432 - val_loss: 0.0792 - val_accuracy: 0.9744\n",
|
||
"Epoch 191/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5060 - accuracy: 0.9773 - val_loss: 0.0652 - val_accuracy: 0.9744\n",
|
||
"Epoch 192/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.5153 - accuracy: 0.9432 - val_loss: 0.0433 - val_accuracy: 0.9744\n",
|
||
"Epoch 193/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.0084 - accuracy: 1.0000 - val_loss: 0.0521 - val_accuracy: 0.9744\n",
|
||
"Epoch 194/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.2616 - accuracy: 0.9773 - val_loss: 0.0260 - val_accuracy: 0.9744\n",
|
||
"Epoch 195/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.8557 - accuracy: 0.9205 - val_loss: 0.0740 - val_accuracy: 0.9744\n",
|
||
"Epoch 196/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3679 - accuracy: 0.9659 - val_loss: 0.4906 - val_accuracy: 0.9487\n",
|
||
"Epoch 197/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 1.6092 - accuracy: 0.9659 - val_loss: 0.9070 - val_accuracy: 0.9744\n",
|
||
"Epoch 198/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 1.4481 - accuracy: 0.9773 - val_loss: 0.6460 - val_accuracy: 0.9744\n",
|
||
"Epoch 199/200\n",
|
||
"3/3 [==============================] - 0s 7ms/step - loss: 0.7262 - accuracy: 0.9659 - val_loss: 0.5395 - val_accuracy: 0.8974\n",
|
||
"Epoch 200/200\n",
|
||
"3/3 [==============================] - 0s 8ms/step - loss: 0.3021 - accuracy: 0.9318 - val_loss: 0.0580 - val_accuracy: 0.9744\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<tensorflow.python.keras.callbacks.History at 0x185bb8bc9c8>"
|
||
]
|
||
},
|
||
"execution_count": 84,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier word er getraint met de training waardes. Met 200 als \n",
|
||
"het aantal epochs. \n",
|
||
"We hebben hier ook gekozen om als validation_split 0.3 te \n",
|
||
"kiezen. Dit betekend dat er 30% van de waardes gebruikt wordt\n",
|
||
"om te trainen. De overige worden gebruikt om te testen.\n",
|
||
"\"\"\"\n",
|
||
"model.fit(X_train, y_train, epochs=200, validation_split=0.3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 85,
|
||
"id": "be9f2f17",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier worden waarde van de test waarde voorspelt.\n",
|
||
"\"\"\"\n",
|
||
"y_pred = model.predict(X_test)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 86,
|
||
"id": "8755dd0a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[5.6894045e-17, 8.8579909e-25, 6.5820859e-06, 0.0000000e+00,\n",
|
||
" 9.9999344e-01, 0.0000000e+00, 0.0000000e+00],\n",
|
||
" [1.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
|
||
" 0.0000000e+00, 0.0000000e+00, 0.0000000e+00],\n",
|
||
" [0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
|
||
" 0.0000000e+00, 1.0000000e+00, 0.0000000e+00],\n",
|
||
" [1.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
|
||
" 0.0000000e+00, 0.0000000e+00, 0.0000000e+00],\n",
|
||
" [4.9131124e-16, 1.9639882e-07, 1.3309444e-01, 1.7775484e-13,\n",
|
||
" 8.6690539e-01, 0.0000000e+00, 0.0000000e+00]], dtype=float32)"
|
||
]
|
||
},
|
||
"execution_count": 86,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"De eerste 5 elementen uit de lijst waar de voorspellende waardes zitten \n",
|
||
"worden weergegeven.\n",
|
||
"\"\"\"\n",
|
||
"y_pred[:5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 87,
|
||
"id": "aca71c4d",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"pakt de hoogste waarde plus hun axis om weer te geven in de \n",
|
||
"classification_report.\n",
|
||
"\"\"\"\n",
|
||
"y_test_class = np.argmax(y_test, axis=1)\n",
|
||
"y_pred_class = np.argmax(y_pred, axis=1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 88,
|
||
"id": "d8412c09",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" 0 1.00 1.00 1.00 6\n",
|
||
" 1 1.00 1.00 1.00 3\n",
|
||
" 2 1.00 0.33 0.50 3\n",
|
||
" 3 1.00 1.00 1.00 2\n",
|
||
" 4 0.85 1.00 0.92 11\n",
|
||
" 5 1.00 1.00 1.00 4\n",
|
||
" 6 1.00 1.00 1.00 3\n",
|
||
"\n",
|
||
" accuracy 0.94 32\n",
|
||
" macro avg 0.98 0.90 0.92 32\n",
|
||
"weighted avg 0.95 0.94 0.92 32\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier worden de waardes in een classification_report uit geprint. We zien dat\n",
|
||
"het netwerk vrij accuraat is, alleen de recall bij categorie 2 is laag.\n",
|
||
"\"\"\"\n",
|
||
"print(classification_report(y_test_class, y_pred_class))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 89,
|
||
"id": "e7880a56",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[ 6, 0, 0, 0, 0, 0, 0],\n",
|
||
" [ 0, 3, 0, 0, 0, 0, 0],\n",
|
||
" [ 0, 0, 1, 0, 2, 0, 0],\n",
|
||
" [ 0, 0, 0, 2, 0, 0, 0],\n",
|
||
" [ 0, 0, 0, 0, 11, 0, 0],\n",
|
||
" [ 0, 0, 0, 0, 0, 4, 0],\n",
|
||
" [ 0, 0, 0, 0, 0, 0, 3]], dtype=int64)"
|
||
]
|
||
},
|
||
"execution_count": 89,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\"\"\"\n",
|
||
"Hier wordt gekeken hoe accuraat de classification is.\n",
|
||
"Een confusion_matrix is een matrix gevormd door te vergelijken met de test\n",
|
||
"waardes en de voorspelde waardes. Kijken hoeveel er goed en hoeveel er fout \n",
|
||
"zijn voorspeld. We kunnen zien dat er 2 keer een fout gemaakt is bij \n",
|
||
"trainwaarde 2 en testwaarde 4.\n",
|
||
"\"\"\"\n",
|
||
"confusion_matrix(y_test_class, y_pred_class)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6042b086",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Week 6"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "558dba9a",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Opdracht 6.1: ZTDL 6: Convolutional Neural Networks – MNIST"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1935903b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#maak een sequentieel model aan\n",
|
||
"model = Sequential() \n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"Voeg een 2D convolution layer toe met 32 output filters, een kernel van 3x3\n",
|
||
"en een input shape van 28x28 grootte en 1 layer.\n",
|
||
"\"\"\"\n",
|
||
"model.add(Conv2D(32,(3,3),input_shape={28,28,1}))\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"Voeg een maxpool2d laag toe met een size van 2x2. Deze laag pakt het grootste\n",
|
||
"element uit een 2x2 vierkant in elke laag.\n",
|
||
"\"\"\"\n",
|
||
"model.add(MaxPool2D(pool_size=(2,2)))\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"Voeg een activation laag toe die de relu functie gebruikt. Deze functie maakt\n",
|
||
"van negatieve getallen een 0. Deze functie wordt uitgevoerd op de som van alle\n",
|
||
"waarden op de laagseizoen onder de kernel.\n",
|
||
"\"\"\"\n",
|
||
"model.add(Activation('relu'))\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"door een flatten laag toe te voegen worden alle lagen achter elkaar gezet\n",
|
||
"zodat deze makkelijker als input gebruikt kunnen worden voor de volgende lagen.\n",
|
||
"bron:\n",
|
||
"https://www.superdatascience.com/blogs/convolutional-neural-networks-cnn-step-3-flattening\n",
|
||
"\"\"\"\n",
|
||
"model.add(Flatten())\n",
|
||
"\n",
|
||
"\n",
|
||
"# voeg nog een relu activatie laag toe met 128.\n",
|
||
"model.add(Dense(128,activation='relu'))\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"Voeg een activatielaag toe die de softmax functie gebruikt zodat we een\n",
|
||
"percentage van categoriën krijgen als resultaat. Deze laag heeft 10 outputs\n",
|
||
"\"\"\"\n",
|
||
"model.add(Dense(10,activation='softmax'))\n",
|
||
"\n",
|
||
"\"\"\"\n",
|
||
"compileer het model met de categorical crossentropy loss function,\n",
|
||
"en de rmsprop als optimizer.\n",
|
||
"We willen de accuracy vergelijken door deze als metric mee te geven.\n",
|
||
"\n",
|
||
"TODO optimizer en loss uitleggen\n",
|
||
"\"\"\"\n",
|
||
"model.compile(loss='categorical_crossentropy',\n",
|
||
" optimizer='rmsprop',\n",
|
||
" metrics=['accuracy'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ea5be5e2",
|
||
"metadata": {},
|
||
"source": [
|
||
"## De eindopdracht"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c044b378",
|
||
"metadata": {},
|
||
"source": [
|
||
"We hebben de video bekeken en hebben besloten een binaire classificatie te testen van foto's waar wij op staan. Hierbij zullen we de foto's onderverdelen en testen op of Sem of Lars op de foto staat. We hebben dus ook een dataset gemaakt met foto's van ons allebei."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "93b488c5",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Populating the interactive namespace from numpy and matplotlib\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"%pylab inline\n",
|
||
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
|
||
"from tensorflow.keras.preprocessing import image\n",
|
||
"import tensorflow as tf\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import os\n",
|
||
"import matplotlib.image as mpimg\n",
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "089b7fed",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"img = image.load_img('../data/imgs/test/sem/1.png')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "07fd9543",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<matplotlib.image.AxesImage at 0x29c300e49c8>"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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\n",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.imshow(img)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"id": "054c0e39",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[[0.84705883, 0.8745098 , 0.8039216 , 1. ],\n",
|
||
" [0.84705883, 0.8745098 , 0.8039216 , 1. ],\n",
|
||
" [0.84705883, 0.8745098 , 0.8039216 , 1. ],\n",
|
||
" ...,\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84705883, 0.8784314 , 0.827451 , 1. ]],\n",
|
||
"\n",
|
||
" [[0.84705883, 0.8745098 , 0.8039216 , 1. ],\n",
|
||
" [0.84705883, 0.8745098 , 0.8039216 , 1. ],\n",
|
||
" [0.84313726, 0.87058824, 0.8 , 1. ],\n",
|
||
" ...,\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84705883, 0.8784314 , 0.827451 , 1. ]],\n",
|
||
"\n",
|
||
" [[0.8392157 , 0.8666667 , 0.79607844, 1. ],\n",
|
||
" [0.8392157 , 0.8666667 , 0.79607844, 1. ],\n",
|
||
" [0.8392157 , 0.8666667 , 0.79607844, 1. ],\n",
|
||
" ...,\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84313726, 0.8745098 , 0.8235294 , 1. ],\n",
|
||
" [0.84705883, 0.8784314 , 0.827451 , 1. ]],\n",
|
||
"\n",
|
||
" ...,\n",
|
||
"\n",
|
||
" [[0.19607843, 0.11372549, 0.24313726, 1. ],\n",
|
||
" [0.19607843, 0.11372549, 0.24313726, 1. ],\n",
|
||
" [0.2 , 0.11764706, 0.24705882, 1. ],\n",
|
||
" ...,\n",
|
||
" [0.18431373, 0.09411765, 0.20784314, 1. ],\n",
|
||
" [0.18431373, 0.09411765, 0.20784314, 1. ],\n",
|
||
" [0.1882353 , 0.09803922, 0.21176471, 1. ]],\n",
|
||
"\n",
|
||
" [[0.19215687, 0.10980392, 0.23529412, 1. ],\n",
|
||
" [0.19215687, 0.10980392, 0.23921569, 1. ],\n",
|
||
" [0.19607843, 0.11372549, 0.23921569, 1. ],\n",
|
||
" ...,\n",
|
||
" [0.1882353 , 0.09803922, 0.21176471, 1. ],\n",
|
||
" [0.18431373, 0.09411765, 0.20784314, 1. ],\n",
|
||
" [0.1882353 , 0.09803922, 0.21176471, 1. ]],\n",
|
||
"\n",
|
||
" [[0.19215687, 0.10980392, 0.23137255, 1. ],\n",
|
||
" [0.19215687, 0.10980392, 0.23137255, 1. ],\n",
|
||
" [0.19607843, 0.11372549, 0.23529412, 1. ],\n",
|
||
" ...,\n",
|
||
" [0.1882353 , 0.09803922, 0.21176471, 1. ],\n",
|
||
" [0.19607843, 0.10588235, 0.21960784, 1. ],\n",
|
||
" [0.19607843, 0.10588235, 0.21960784, 1. ]]], dtype=float32)"
|
||
]
|
||
},
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"img2 = mpimg.imread('../data/imgs/training/sem/6.png')\n",
|
||
"img2"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"id": "9265e6f0",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"train = ImageDataGenerator()\n",
|
||
"validation = ImageDataGenerator()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"id": "ecea5aa3",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Found 20 images belonging to 2 classes.\n",
|
||
"Found 7 images belonging to 2 classes.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"train_dataset = train.flow_from_directory('../data/imgs/training',\n",
|
||
" target_size=(200,200),\n",
|
||
" batch_size=3,\n",
|
||
" class_mode = 'binary')\n",
|
||
"\n",
|
||
"validation_dataset = train.flow_from_directory('../data/imgs/validation',\n",
|
||
" target_size=(200,200),\n",
|
||
" batch_size=3,\n",
|
||
" class_mode = 'binary')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 30,
|
||
"id": "cd57c7dd",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"{'lars': 0, 'sem': 1}"
|
||
]
|
||
},
|
||
"execution_count": 30,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"train_dataset.class_indices"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 34,
|
||
"id": "cd2f1824",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([1, 1, 1, 1, 1, 1, 1])"
|
||
]
|
||
},
|
||
"execution_count": 34,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"train_dataset.classes"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 33,
|
||
"id": "265a5e2b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"model = tf.keras.models.Sequential()\n",
|
||
"\n",
|
||
"model.add(tf.keras.layers.Conv2D(16,(3,3),activation='relu',\n",
|
||
" input_shape=(200,200,4)))\n",
|
||
"model.add(tf.keras.layers.MaxPool2D(2,2))\n",
|
||
"\n",
|
||
"model.add(tf.keras.layers.Conv2D(32,(3,3),activation='relu'))\n",
|
||
"model.add(tf.keras.layers.MaxPool2D(2,2))\n",
|
||
"\n",
|
||
"model.add(tf.keras.layers.Conv2D(64,(3,3),activation='relu'))\n",
|
||
"model.add(tf.keras.layers.MaxPool2D(2,2))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f8941d14",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.7.10"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|