Neural Network Training using Keras
This notebook implements a neural network for classifying the Iris dataset using Keras instead of manually programmed functions.
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from sklearn.metrics import confusion_matrix, classification_report
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
# Load data from binary dataset
data = np.load("iris_train_test_data.npz")
# Extract data
X_train, y_train, X_test, y_test = data["X_train"], data["y_train"], data["X_test"], data["y_test"]
print("Dataset loaded successfully.")
Dataset loaded successfully.
Defining and Training the Neural Network
We will use Sequential from Keras to define our neural network:
- Input Layer: The input size is determined by
X_train.shape[1].
- Hidden Layer: One hidden layer with 5 neurons, using the sigmoid activation function.
- Output Layer: The output layer has 3 neurons (one per class) and uses the softmax activation function.
- Optimizer: Adam optimizer is used.
- Loss Function: Categorical cross-entropy is used since we have a multi-class classification problem.
- Batch Size: Set to
10.
- Epochs: Training will run for
1000 epochs.
# Define the neural network model
from tensorflow.keras.layers import Input
model = Sequential([
Input(shape=(X_train.shape[1],)), # Explicitly define input layer
Dense(5, activation='sigmoid'),
Dense(3, activation='softmax') # Output layer with 3 neurons
])
# Compile the model
model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.01),
loss='categorical_crossentropy',
metrics=['accuracy'])
# Train the model
history = model.fit(X_train, y_train, epochs=200, batch_size=X_train.shape[0], verbose=1)
print("Training complete.")
Epoch 1/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 408ms/step - accuracy: 0.3238 - loss: 1.4010
Epoch 2/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.3238 - loss: 1.3755
Epoch 3/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3238 - loss: 1.3517
Epoch 4/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3238 - loss: 1.3294
Epoch 5/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.3238 - loss: 1.3083
Epoch 6/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.3238 - loss: 1.2884
Epoch 7/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.3238 - loss: 1.2696
Epoch 8/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3238 - loss: 1.2520
Epoch 9/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3238 - loss: 1.2354
Epoch 10/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.3238 - loss: 1.2199
Epoch 11/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.3238 - loss: 1.2055
Epoch 12/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.3238 - loss: 1.1921
Epoch 13/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.3238 - loss: 1.1798
Epoch 14/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.3238 - loss: 1.1685
Epoch 15/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.3238 - loss: 1.1581
Epoch 16/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.3238 - loss: 1.1488
Epoch 17/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.3238 - loss: 1.1403
Epoch 18/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3048 - loss: 1.1328
Epoch 19/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.2857 - loss: 1.1260
Epoch 20/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.2667 - loss: 1.1201
Epoch 21/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.3333 - loss: 1.1148
Epoch 22/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - accuracy: 0.3714 - loss: 1.1102
Epoch 23/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.4476 - loss: 1.1061
Epoch 24/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - accuracy: 0.4381 - loss: 1.1026
Epoch 25/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.4286 - loss: 1.0995
Epoch 26/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - accuracy: 0.4095 - loss: 1.0967
Epoch 27/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - accuracy: 0.4000 - loss: 1.0943
Epoch 28/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - accuracy: 0.4000 - loss: 1.0921
Epoch 29/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - accuracy: 0.3905 - loss: 1.0902
Epoch 30/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - accuracy: 0.3714 - loss: 1.0884
Epoch 31/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - accuracy: 0.3524 - loss: 1.0867
Epoch 32/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.3524 - loss: 1.0851
Epoch 33/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.3524 - loss: 1.0836
Epoch 34/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6667 - loss: 1.0820
Epoch 35/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - accuracy: 0.6762 - loss: 1.0805
Epoch 36/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - accuracy: 0.6762 - loss: 1.0789
Epoch 37/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - accuracy: 0.6762 - loss: 1.0774
Epoch 38/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 1.0758
Epoch 39/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 1.0741
Epoch 40/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 1.0724
Epoch 41/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 1.0707
Epoch 42/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6762 - loss: 1.0689
Epoch 43/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6762 - loss: 1.0670
Epoch 44/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 1.0652
Epoch 45/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 1.0633
Epoch 46/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6762 - loss: 1.0614
Epoch 47/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 1.0594
Epoch 48/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 1.0575
Epoch 49/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6762 - loss: 1.0555
Epoch 50/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6857 - loss: 1.0535
Epoch 51/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6857 - loss: 1.0516
Epoch 52/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6952 - loss: 1.0496
Epoch 53/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.7333 - loss: 1.0476
Epoch 54/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.7333 - loss: 1.0456
Epoch 55/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.7714 - loss: 1.0436
Epoch 56/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.8000 - loss: 1.0416
Epoch 57/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.8667 - loss: 1.0396
Epoch 58/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.8000 - loss: 1.0376
Epoch 59/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8000 - loss: 1.0356
Epoch 60/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.7238 - loss: 1.0336
Epoch 61/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6952 - loss: 1.0316
Epoch 62/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 1.0295
Epoch 63/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 1.0274
Epoch 64/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6667 - loss: 1.0253
Epoch 65/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6667 - loss: 1.0232
Epoch 66/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6667 - loss: 1.0210
Epoch 67/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6667 - loss: 1.0189
Epoch 68/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6667 - loss: 1.0166
Epoch 69/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 1.0144
Epoch 70/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 1.0121
Epoch 71/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 1.0097
Epoch 72/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 1.0073
Epoch 73/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 1.0049
Epoch 74/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 1.0025
Epoch 75/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 1.0000
Epoch 76/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9974
Epoch 77/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.9949
Epoch 78/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9923
Epoch 79/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.9896
Epoch 80/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.9869
Epoch 81/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.9842
Epoch 82/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9814
Epoch 83/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.9786
Epoch 84/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9757
Epoch 85/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.9728
Epoch 86/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9699
Epoch 87/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6667 - loss: 0.9669
Epoch 88/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - accuracy: 0.6667 - loss: 0.9639
Epoch 89/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6667 - loss: 0.9608
Epoch 90/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6667 - loss: 0.9577
Epoch 91/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.9545
Epoch 92/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.9513
Epoch 93/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.9481
Epoch 94/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9448
Epoch 95/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9415
Epoch 96/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6762 - loss: 0.9382
Epoch 97/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9348
Epoch 98/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9313
Epoch 99/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6762 - loss: 0.9278
Epoch 100/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9243
Epoch 101/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 0.9207
Epoch 102/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9171
Epoch 103/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9135
Epoch 104/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6762 - loss: 0.9098
Epoch 105/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 17ms/step - accuracy: 0.6762 - loss: 0.9061
Epoch 106/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6762 - loss: 0.9023
Epoch 107/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6762 - loss: 0.8985
Epoch 108/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6762 - loss: 0.8947
Epoch 109/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - accuracy: 0.6667 - loss: 0.8908
Epoch 110/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6667 - loss: 0.8869
Epoch 111/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6667 - loss: 0.8829
Epoch 112/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.8789
Epoch 113/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.8749
Epoch 114/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.8709
Epoch 115/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.8668
Epoch 116/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.8627
Epoch 117/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.8586
Epoch 118/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.8544
Epoch 119/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6667 - loss: 0.8503
Epoch 120/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6667 - loss: 0.8460
Epoch 121/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.6667 - loss: 0.8418
Epoch 122/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6667 - loss: 0.8376
Epoch 123/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6667 - loss: 0.8333
Epoch 124/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6667 - loss: 0.8290
Epoch 125/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6667 - loss: 0.8247
Epoch 126/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 0.8204
Epoch 127/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6762 - loss: 0.8160
Epoch 128/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6762 - loss: 0.8117
Epoch 129/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6762 - loss: 0.8073
Epoch 130/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6762 - loss: 0.8029
Epoch 131/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6857 - loss: 0.7985
Epoch 132/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6857 - loss: 0.7941
Epoch 133/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6857 - loss: 0.7897
Epoch 134/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6857 - loss: 0.7853
Epoch 135/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6857 - loss: 0.7809
Epoch 136/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - accuracy: 0.6857 - loss: 0.7765
Epoch 137/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6857 - loss: 0.7721
Epoch 138/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6857 - loss: 0.7677
Epoch 139/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - accuracy: 0.6857 - loss: 0.7633
Epoch 140/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6857 - loss: 0.7589
Epoch 141/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - accuracy: 0.6857 - loss: 0.7545
Epoch 142/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.6857 - loss: 0.7502
Epoch 143/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6857 - loss: 0.7458
Epoch 144/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6857 - loss: 0.7415
Epoch 145/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6857 - loss: 0.7371
Epoch 146/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.6857 - loss: 0.7328
Epoch 147/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6857 - loss: 0.7285
Epoch 148/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6857 - loss: 0.7243
Epoch 149/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.6857 - loss: 0.7200
Epoch 150/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6952 - loss: 0.7158
Epoch 151/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.6952 - loss: 0.7116
Epoch 152/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6952 - loss: 0.7074
Epoch 153/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.6952 - loss: 0.7033
Epoch 154/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6952 - loss: 0.6992
Epoch 155/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.6952 - loss: 0.6951
Epoch 156/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.7048 - loss: 0.6910
Epoch 157/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.7048 - loss: 0.6870
Epoch 158/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - accuracy: 0.7048 - loss: 0.6831
Epoch 159/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - accuracy: 0.7048 - loss: 0.6791
Epoch 160/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - accuracy: 0.7048 - loss: 0.6752
Epoch 161/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - accuracy: 0.7143 - loss: 0.6714
Epoch 162/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.7238 - loss: 0.6675
Epoch 163/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.7333 - loss: 0.6638
Epoch 164/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.7429 - loss: 0.6600
Epoch 165/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.7524 - loss: 0.6563
Epoch 166/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.7524 - loss: 0.6527
Epoch 167/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.7619 - loss: 0.6491
Epoch 168/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.7619 - loss: 0.6455
Epoch 169/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.7714 - loss: 0.6420
Epoch 170/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.7714 - loss: 0.6385
Epoch 171/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.7714 - loss: 0.6351
Epoch 172/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.7714 - loss: 0.6317
Epoch 173/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.7810 - loss: 0.6284
Epoch 174/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.7810 - loss: 0.6251
Epoch 175/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.7810 - loss: 0.6218
Epoch 176/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8095 - loss: 0.6186
Epoch 177/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8095 - loss: 0.6155
Epoch 178/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.8095 - loss: 0.6123
Epoch 179/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.8381 - loss: 0.6093
Epoch 180/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.8381 - loss: 0.6063
Epoch 181/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8381 - loss: 0.6033
Epoch 182/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 24ms/step - accuracy: 0.8381 - loss: 0.6004
Epoch 183/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.8381 - loss: 0.5975
Epoch 184/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.8381 - loss: 0.5946
Epoch 185/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.8381 - loss: 0.5918
Epoch 186/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8381 - loss: 0.5891
Epoch 187/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.8381 - loss: 0.5864
Epoch 188/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.8381 - loss: 0.5837
Epoch 189/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8476 - loss: 0.5811
Epoch 190/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step - accuracy: 0.8476 - loss: 0.5785
Epoch 191/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8476 - loss: 0.5759
Epoch 192/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8476 - loss: 0.5734
Epoch 193/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.8571 - loss: 0.5709
Epoch 194/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 22ms/step - accuracy: 0.8571 - loss: 0.5685
Epoch 195/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 21ms/step - accuracy: 0.8571 - loss: 0.5661
Epoch 196/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8571 - loss: 0.5638
Epoch 197/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 23ms/step - accuracy: 0.8571 - loss: 0.5615
Epoch 198/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - accuracy: 0.8571 - loss: 0.5592
Epoch 199/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8571 - loss: 0.5569
Epoch 200/200
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step - accuracy: 0.8571 - loss: 0.5547
Training complete.
Model Evaluation
We now evaluate the trained model using the test set (X_test, y_test). The confusion matrix will be displayed to assess classification performance.
# Predict on test set
y_pred = model.predict(X_test)
y_pred_classes = np.argmax(y_pred, axis=1)
y_test_classes = np.argmax(y_test, axis=1)
# Compute confusion matrix
cm = confusion_matrix(y_test_classes, y_pred_classes)
# Convert to DataFrame for better visualization
df_cm = pd.DataFrame(cm, index=['setosa', 'versicolor', 'virginica'],
columns=['setosa', 'versicolor', 'virginica'])
# Plot confusion matrix
plt.figure(figsize=(6,6))
sns.heatmap(df_cm, annot=True, fmt="d", cmap="Blues", linewidths=0.5)
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.title('Confusion Matrix')
plt.show()
# Display classification report
print(classification_report(y_test_classes, y_pred_classes, target_names=['setosa', 'versicolor', 'virginica']))
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step
precision recall f1-score support
setosa 1.00 1.00 1.00 14
versicolor 0.84 1.00 0.91 16
virginica 1.00 0.80 0.89 15
accuracy 0.93 45
macro avg 0.95 0.93 0.93 45
weighted avg 0.94 0.93 0.93 45
