The Iris Dataset Example with Keras 2.8 on Windows 11

Posted on April 27, 2022 by jamesdmccaffrey

Because neural network code libraries (TensorFlow, Keras, PyTorch) constantly change, I redo a set of basic examples every few months to make sure no breaking changes have been introduced. A few days ago, I coded up an example of the Iris Dataset problem using the latest version of PyTorch. So, I figured I’d revisit the Iris problem using the current version of Keras/TensorFlow (version 2.8) on Windows 11.

I installed TensorFlow + Keras for Windows CPU using the .whl file at https://pypi.org/project/tensorflow-cpu/#files — tensorflow_cpu-2.8.0-cp37-cp37m-win_amd64.whl (because I was using Anaconda 2020.02 with Python 3.7.6).


Side-by-side comparison of PyTorch 1.10 (left) and Keras 2.8 (right). Very similar results.

See https://jamesmccaffreyblog.com/2022/04/20/the-iris-dataset-example-with-pytorch-1-10-on-windows-11/ for the Iris data used and the PyTorch code.

I implemented the Keras code to try and make it as similar as possible to my PyTorch version. I couldn’t replicate the PyTorch version exactly, but I got pretty close. The Keras neural network is 4-7-3 with tanh() hidden activation and softmax() output activation. I used uniform weight initialization and zero bias initialization. For training, I used a batch size of 4, and stochastic gradient descent with a learning rate = 0.01.

Overall, I slightly prefer using PyTorch over Keras, but I like both libraries. PyTorch works at a lower level which means you have to write a bit more code than when using Keras. But PyTorch is much more flexible than Keras. Because Keras is essentially a wrapper over TensorFlow, you can get maximum flexibility by using TensorFlow directly — but I much prefer using PyTorch to TensorFlow.

It’s impossible to get good statistics, but it’s my strong impression that the use of PyTorch is increasing more rapidly than the use of Keras/TensorFlow. PyTorch and Keras/TensorFlow are different enough that it’s usually not feasible to use both in a work environment, so all my colleagues have picked one or the other — I’d estimate about 70% of the groups I work with use PyTorch and 30% use Keras/TensorFlow.


Keras, TensorFlow, and PyTorch neural networks use different styles. Movies can have different styles too. Here are three of my favorite movie versions of “Treasure Island” written by Robert Lewis Stevenson in 1883. Left: The 1950 version with Robert Newton as Long John Silver. Center: The 1934 version with Wallace Beery as Silver. Right: The 1996 Muppet version with Tim Curry as Silver.

Keras demo code:

# iris_tfk.py

# Anaconda3-2020.02  (Python 3.7.6)
# TensorFlow 2.8.0 (includes KerasTF 2.8.0)
# Windows 10/11

import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

import numpy as np
import tensorflow as tf
from tensorflow import keras as K

# -----------------------------------------------------------

class MyLogger(K.callbacks.Callback):
  def __init__(self, n):
    self.n = n   # print loss & acc every n epochs

  def on_epoch_end(self, epoch, logs={}):
    if epoch % self.n == 0:
      curr_loss = logs.get('loss')
      curr_acc = logs.get('accuracy') * 100
      print("epoch = %4d  |  loss = %0.6f  |  acc = %0.2f%%" % \
(epoch, curr_loss, curr_acc))

# -----------------------------------------------------------

def main():
  # 0. get started
  print("\nBegin Iris dataset using Keras/TensorFlow ")
  np.random.seed(1)
  tf.random.set_seed(1)

  print("\nLoading Iris train and test data into memory ")
  # 5.0, 3.5, 1.3, 0.3, 0
  # setosa = 0, versicolor = 1, virginica = 2

  # 1. load data
  train_file = ".\\Data\\iris_train.txt"  # ordinal encoded
  train_x = np.loadtxt(train_file, usecols=[0,1,2,3],
    delimiter=",", comments="#", dtype=np.float32)
  train_y = np.loadtxt(train_file, usecols=[4],
    delimiter=",", comments="#", dtype=np.int64)
  train_y = K.utils.to_categorical(train_y)  # to one-hot

  test_file = ".\\Data\\iris_test.txt"
  test_x = np.loadtxt(test_file, usecols=[0,1,2,3],
    delimiter=",", comments="#", dtype=np.float32)
  test_y = np.loadtxt(test_file, usecols=[4],
    delimiter=",", comments="#", dtype=np.int64)
  test_y = K.utils.to_categorical(test_y)

# -----------------------------------------------------------

  # 2. create network
  print("\nCreating 4-7-3 neural network ")
  net = K.models.Sequential()
  initer = K.initializers.RandomUniform(-0.01, +0.01)
  net.add(K.layers.Dense(units=7, input_dim=4,
    activation='tanh', kernel_initializer=initer,
    bias_initializer='zeros'))
  net.add(K.layers.Dense(units=3, activation='softmax',
    kernel_initializer=initer, bias_initializer='zeros'))
  opt = K.optimizers.SGD(learning_rate=0.01)
  net.compile(loss='categorical_crossentropy',
    optimizer=opt, metrics=['accuracy'])

  my_logger = MyLogger(n=10)

# -----------------------------------------------------------

  # 3. train model
  print("\nbat_size = 4 ")
  print("loss = categorical_crossentropy ")
  print("optimizer = SGD")
  print("max_epochs = 50 ")
  print("lrn_rate = 0.010 ")
  print("\nStarting training ")
  h = net.fit(train_x, train_y, batch_size=4,
    epochs=50, verbose=0, callbacks=[my_logger])  # 1 = chatty
  print("Done ")

# -----------------------------------------------------------

  # 4. evaluate model accuracy
  print("\nComputing model accuracy")
  eval = net.evaluate(test_x, test_y, verbose=0)
  print("Accuracy on test data: %0.4f " % eval[1] )

# -----------------------------------------------------------

  # 4b. inspect model
  # np.set_printoptions(precision=4, suppress=True)
  # wts = net.get_weights()
  # print("\nTrained model weights and biases: ")
  # for ar in wts:
  #   print(ar)
  #   print("")

  # 5. make a prediction
  print("\nPredicting species for [6.1, 3.1, 5.1, 1.1]: ")
  np.set_printoptions(precision=4)
  X = np.array([[6.1, 3.1, 5.1, 1.1]], dtype=np.float32)
  probs = net.predict(X)
  print(probs)  # pseudo-probs

  # 6. save model (full model approach)
  print("\nSaving trained model ")
  # net.save_weights(".\\Models\\iris_model.h5")
  # net.save(".\\Models\\iris_model.h5")

  print("\nEnd Iris demo")

if __name__=="__main__":
  main()

Training data:

# iris_train.txt
#
# https://archive.ics.uci.edu/ml/datasets/iris
# sepal len, sepal wid, petal len, petal wid, species
# 0 = setosa, 1 = versicolor, 2 = virginica
#
5.1, 3.5, 1.4, 0.2, 0
4.9, 3.0, 1.4, 0.2, 0
4.7, 3.2, 1.3, 0.2, 0
4.6, 3.1, 1.5, 0.2, 0
5.0, 3.6, 1.4, 0.2, 0
5.4, 3.9, 1.7, 0.4, 0
4.6, 3.4, 1.4, 0.3, 0
5.0, 3.4, 1.5, 0.2, 0
4.4, 2.9, 1.4, 0.2, 0
4.9, 3.1, 1.5, 0.1, 0
5.4, 3.7, 1.5, 0.2, 0
4.8, 3.4, 1.6, 0.2, 0
4.8, 3.0, 1.4, 0.1, 0
4.3, 3.0, 1.1, 0.1, 0
5.8, 4.0, 1.2, 0.2, 0
5.7, 4.4, 1.5, 0.4, 0
5.4, 3.9, 1.3, 0.4, 0
5.1, 3.5, 1.4, 0.3, 0
5.7, 3.8, 1.7, 0.3, 0
5.1, 3.8, 1.5, 0.3, 0
5.4, 3.4, 1.7, 0.2, 0
5.1, 3.7, 1.5, 0.4, 0
4.6, 3.6, 1.0, 0.2, 0
5.1, 3.3, 1.7, 0.5, 0
4.8, 3.4, 1.9, 0.2, 0
5.0, 3.0, 1.6, 0.2, 0
5.0, 3.4, 1.6, 0.4, 0
5.2, 3.5, 1.5, 0.2, 0
5.2, 3.4, 1.4, 0.2, 0
4.7, 3.2, 1.6, 0.2, 0
4.8, 3.1, 1.6, 0.2, 0
5.4, 3.4, 1.5, 0.4, 0
5.2, 4.1, 1.5, 0.1, 0
5.5, 4.2, 1.4, 0.2, 0
4.9, 3.1, 1.5, 0.1, 0
5.0, 3.2, 1.2, 0.2, 0
5.5, 3.5, 1.3, 0.2, 0
4.9, 3.1, 1.5, 0.1, 0
4.4, 3.0, 1.3, 0.2, 0
5.1, 3.4, 1.5, 0.2, 0
7.0, 3.2, 4.7, 1.4, 1
6.4, 3.2, 4.5, 1.5, 1
6.9, 3.1, 4.9, 1.5, 1
5.5, 2.3, 4.0, 1.3, 1
6.5, 2.8, 4.6, 1.5, 1
5.7, 2.8, 4.5, 1.3, 1
6.3, 3.3, 4.7, 1.6, 1
4.9, 2.4, 3.3, 1.0, 1
6.6, 2.9, 4.6, 1.3, 1
5.2, 2.7, 3.9, 1.4, 1
5.0, 2.0, 3.5, 1.0, 1
5.9, 3.0, 4.2, 1.5, 1
6.0, 2.2, 4.0, 1.0, 1
6.1, 2.9, 4.7, 1.4, 1
5.6, 2.9, 3.6, 1.3, 1
6.7, 3.1, 4.4, 1.4, 1
5.6, 3.0, 4.5, 1.5, 1
5.8, 2.7, 4.1, 1.0, 1
6.2, 2.2, 4.5, 1.5, 1
5.6, 2.5, 3.9, 1.1, 1
5.9, 3.2, 4.8, 1.8, 1
6.1, 2.8, 4.0, 1.3, 1
6.3, 2.5, 4.9, 1.5, 1
6.1, 2.8, 4.7, 1.2, 1
6.4, 2.9, 4.3, 1.3, 1
6.6, 3.0, 4.4, 1.4, 1
6.8, 2.8, 4.8, 1.4, 1
6.7, 3.0, 5.0, 1.7, 1
6.0, 2.9, 4.5, 1.5, 1
5.7, 2.6, 3.5, 1.0, 1
5.5, 2.4, 3.8, 1.1, 1
5.5, 2.4, 3.7, 1.0, 1
5.8, 2.7, 3.9, 1.2, 1
6.0, 2.7, 5.1, 1.6, 1
5.4, 3.0, 4.5, 1.5, 1
6.0, 3.4, 4.5, 1.6, 1
6.7, 3.1, 4.7, 1.5, 1
6.3, 2.3, 4.4, 1.3, 1
5.6, 3.0, 4.1, 1.3, 1
5.5, 2.5, 4.0, 1.3, 1
6.3, 3.3, 6.0, 2.5, 2
5.8, 2.7, 5.1, 1.9, 2
7.1, 3.0, 5.9, 2.1, 2
6.3, 2.9, 5.6, 1.8, 2
6.5, 3.0, 5.8, 2.2, 2
7.6, 3.0, 6.6, 2.1, 2
4.9, 2.5, 4.5, 1.7, 2
7.3, 2.9, 6.3, 1.8, 2
6.7, 2.5, 5.8, 1.8, 2
7.2, 3.6, 6.1, 2.5, 2
6.5, 3.2, 5.1, 2.0, 2
6.4, 2.7, 5.3, 1.9, 2
6.8, 3.0, 5.5, 2.1, 2
5.7, 2.5, 5.0, 2.0, 2
5.8, 2.8, 5.1, 2.4, 2
6.4, 3.2, 5.3, 2.3, 2
6.5, 3.0, 5.5, 1.8, 2
7.7, 3.8, 6.7, 2.2, 2
7.7, 2.6, 6.9, 2.3, 2
6.0, 2.2, 5.0, 1.5, 2
6.9, 3.2, 5.7, 2.3, 2
5.6, 2.8, 4.9, 2.0, 2
7.7, 2.8, 6.7, 2.0, 2
6.3, 2.7, 4.9, 1.8, 2
6.7, 3.3, 5.7, 2.1, 2
7.2, 3.2, 6.0, 1.8, 2
6.2, 2.8, 4.8, 1.8, 2
6.1, 3.0, 4.9, 1.8, 2
6.4, 2.8, 5.6, 2.1, 2
7.2, 3.0, 5.8, 1.6, 2
7.4, 2.8, 6.1, 1.9, 2
7.9, 3.8, 6.4, 2.0, 2
6.4, 2.8, 5.6, 2.2, 2
6.3, 2.8, 5.1, 1.5, 2
6.1, 2.6, 5.6, 1.4, 2
7.7, 3.0, 6.1, 2.3, 2
6.3, 3.4, 5.6, 2.4, 2
6.4, 3.1, 5.5, 1.8, 2
6.0, 3.0, 4.8, 1.8, 2
6.9, 3.1, 5.4, 2.1, 2

Test data:

# iris_test.txt
#
# https://archive.ics.uci.edu/ml/datasets/iris
# sepal len, width, petal len, width
# setosa = 0, versicolor = 1, virginica = 2
#
5.0, 3.5, 1.3, 0.3, 0
4.5, 2.3, 1.3, 0.3, 0
4.4, 3.2, 1.3, 0.2, 0
5.0, 3.5, 1.6, 0.6, 0
5.1, 3.8, 1.9, 0.4, 0
4.8, 3.0, 1.4, 0.3, 0
5.1, 3.8, 1.6, 0.2, 0
4.6, 3.2, 1.4, 0.2, 0
5.3, 3.7, 1.5, 0.2, 0
5.0, 3.3, 1.4, 0.2, 0
5.5, 2.6, 4.4, 1.2, 1
6.1, 3.0, 4.6, 1.4, 1
5.8, 2.6, 4.0, 1.2, 1
5.0, 2.3, 3.3, 1.0, 1
5.6, 2.7, 4.2, 1.3, 1
5.7, 3.0, 4.2, 1.2, 1
5.7, 2.9, 4.2, 1.3, 1
6.2, 2.9, 4.3, 1.3, 1
5.1, 2.5, 3.0, 1.1, 1
5.7, 2.8, 4.1, 1.3, 1
6.7, 3.1, 5.6, 2.4, 2
6.9, 3.1, 5.1, 2.3, 2
5.8, 2.7, 5.1, 1.9, 2
6.8, 3.2, 5.9, 2.3, 2
6.7, 3.3, 5.7, 2.5, 2
6.7, 3.0, 5.2, 2.3, 2
6.3, 2.5, 5.0, 1.9, 2
6.5, 3.0, 5.2, 2.0, 2
6.2, 3.4, 5.4, 2.3, 2
5.9, 3.0, 5.1, 1.8, 2
This entry was posted in Keras, Miscellaneous. Bookmark the permalink.