Downloaded 144 times
![Deep Learning Classifier for Iris Dataset (2/3)
Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart
# Specify that all features have real-value data
feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
# Build 3 layer DNN with 10, 20, 10 units respectively.
classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
hidden_units=[10, 20, 10],
n_classes=3,
model_dir="/tmp/iris_model")
# Fit model.
classifier.fit(x=training_set.data,
y=training_set.target,
steps=2000)](https://image.slidesharecdn.com/howcanyougetstartedwithmachinelearning-161129101642/85/Introduction-to-Machine-Learning-with-TensorFlow-12-320.jpg)
![Deep Learning Classifier for Iris Dataset (3/3)
Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart
# Evaluate accuracy.
accuracy_score = classifier.evaluate(x=test_set.data,
y=test_set.target)["accuracy"]
print('Accuracy: {0:f}'.format(accuracy_score))
# Classify two new flower samples.
new_samples = np.array([[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=float)
y = classifier.predict(new_samples)
print('Predictions: {}'.format(str(y)))](https://image.slidesharecdn.com/howcanyougetstartedwithmachinelearning-161129101642/85/Introduction-to-Machine-Learning-with-TensorFlow-13-320.jpg)
![Deep Learning Classifier for Iris Dataset (2/3)
Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart
# Specify that all features have real-value data
feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
# Build 3 layer DNN with 10, 20, 10 units respectively.
classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
hidden_units=[10, 20, 10],
n_classes=3,
model_dir="/tmp/iris_model")
# Fit model.
classifier.fit(x=training_set.data,
y=training_set.target,
steps=2000)](https://image.slidesharecdn.com/howcanyougetstartedwithmachinelearning-161129101642/75/Introduction-to-Machine-Learning-with-TensorFlow-12-2048.jpg)
![Deep Learning Classifier for Iris Dataset (3/3)
Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart
# Evaluate accuracy.
accuracy_score = classifier.evaluate(x=test_set.data,
y=test_set.target)["accuracy"]
print('Accuracy: {0:f}'.format(accuracy_score))
# Classify two new flower samples.
new_samples = np.array([[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=float)
y = classifier.predict(new_samples)
print('Predictions: {}'.format(str(y)))](https://image.slidesharecdn.com/howcanyougetstartedwithmachinelearning-161129101642/75/Introduction-to-Machine-Learning-with-TensorFlow-13-2048.jpg)
Uploaded byPaolo Tomeo
Introduction to Machine Learning with TensorFlow
This document introduces TensorFlow, an open source machine learning library for deep learning. It discusses how TensorFlow uses data flow graphs to optimize objective functions and allows computation across CPU and GPU devices. It provides an example of classifying the Iris dataset using TensorFlow's high-level tf.contrib.learn API. It concludes with pointers to additional TensorFlow tutorials and guides.
More Related Content
Similar to Introduction to Machine Learning with TensorFlow
![Agentic Systems and Compliance - A brief intro [1.2]](https://cdn.slidesharecdn.com/ss_thumbnails/agenticsystemsandcompliace-1-251018025303-958a42ec-thumbnail.jpg?width=600ounds&width=560&fit=bounds)
Introduction to Machine Learning with TensorFlow
- 1. Introduction to Machine Learningwith TensorFlow Paolo Tomeo
- 2. Open source MachineLearning library Especially useful for Deep Learning For research and production Apache 2.0 license
- 3. Machine Learning Computer algorithmsfor learning to do something - learning to complete a task - make accurate predictions - to behave intelligently The focus is on automatic methods: learning without any human intervention
- 4. Hello World Image fromhttps://github.com/mnielsen/neural-networks-and-deep-learning ?
- 5. What we seeWhat the computer “sees”
- 6. Complete code import tensorflowas tf mnist = tf.contrib.learn.datasets.load_dataset('mnist') classifier = tf.learn.LinearClassifier(n_classes=10) classifier.fit(mnist.train.images, mnist.train.labels) score = metrics.accuracy_score(mnist.test.labels, classifier.predict(mnist.test.images)) print('Accuracy: {0:f}'.format(score))
- 8. Biologically Inspired ArtificialNeural Network Image from https://visualstudiomagazine.com/articles/2014/06/01/deep-neural-networks.aspx
- 9. Deep Neural Network(DNN)
- 10.
- 11. Deep Learning Classifierfor Iris Dataset (1/3) Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart import tensorflow as tf import numpy as np # Data sets IRIS_TRAINING = "iris_training.csv“ IRIS_TEST = "iris_test.csv" # Load datasets. training_set = tf.contrib.learn.datasets.base.load_csv(filename=IRIS_TRAINING, target_dtype=np.int) test_set = tf.contrib.learn.datasets.base.load_csv(filename=IRIS_TEST, target_dtype=np.int)
- 12. Deep Learning Classifierfor Iris Dataset (2/3) Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart # Specify that all features have real-value data feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)] # Build 3 layer DNN with 10, 20, 10 units respectively. classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns, hidden_units=[10, 20, 10], n_classes=3, model_dir="/tmp/iris_model") # Fit model. classifier.fit(x=training_set.data, y=training_set.target, steps=2000)
- 13. Deep Learning Classifierfor Iris Dataset (3/3) Tutorial from https://www.tensorflow.org/versions/r0.11/tutorials/tflearn/index.html#tf-contrib-learn-quickstart # Evaluate accuracy. accuracy_score = classifier.evaluate(x=test_set.data, y=test_set.target)["accuracy"] print('Accuracy: {0:f}'.format(accuracy_score)) # Classify two new flower samples. new_samples = np.array([[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=float) y = classifier.predict(new_samples) print('Predictions: {}'.format(str(y)))
- 14.
- 15. Lots of tutorialsat tensorflow.org
- 16. Codelab - goo.gl/xGsB9dVideo - goo.gl/B2zYWN TensorFlow for Poets
- 17.
- 18. Claude Monet -Bouquet of Sunflowers Images from the Metropolitan Museum of Art (with permission) Image by @random_forests
- 19. A little moreTensorFlow
- 20. A multidimensional array. Agraph of operations.
- 21. Data Flow Graphs Computationis defined as a directed acyclic graph (DAG) to optimize an objective function Graph is defined in high-level language (Python) Graph is compiled and optimized Graph is executed (in parts or fully) on available low level devices (CPU, GPU) Data (tensors) flow through the graph TensorFlow can compute gradients automatically
- 22. Architecture Core in C++ Frontends: Python and C++ today, community may add more Core TensorFlow Execution System CPU GPU Android iOS ... C++ front end Python front end ...
- 23. tf.contrib.learn TensorFlow’s high-level machinelearning API Easy to configure, train, and evaluate a variety of machine learning models Datasets available in tf.contrib.learn.datasets Warning: any code in tf.contrib is not officially supported, and may change or be removed at any time without notice.
- 24. tf.contrib.learn TensorFlow’s high-level machinelearning API Easy to configure, train, and evaluate a variety of machine learning models Datasets available in tf.contrib.learn.datasets Warning: any code in tf.contrib is not officially supported, and may change or be removed at any time without notice.
- 25.
- 26. tensorflow.org github.com/tensorflow Want to learnmore? Udacity class on Deep Learning, goo.gl/iHssII Guides, codelabs, videos MNIST for Beginners, goo.gl/tx8R2b TF Learn Quickstart, goo.gl/uiefRn TensorFlow for Poets, goo.gl/bVjFIL ML Recipes, goo.gl/KewA03 TensorFlow and Deep Learning without a PhD, goo.gl/pHeXe7 What's Next