sem/CVML-MachineLearning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[ADD] explanation at confusion matrix

Browse Source
This commit is contained in:
Sem van der Hoeven
2021-06-09 10:12:00 +02:00
parent f8e3fdfa4f
commit eabf14ceb5
1 changed files with 4 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
exercises/Jupyter notebook CVML.ipynb
View File

@@ -1859,13 +1859,7 @@
"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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"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",
@@ -2103,13 +2097,7 @@
"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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"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",
@@ -2309,7 +2297,8 @@
"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 voorspelt.\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)"
]