- Related Questions & Answers
- How can a DNN (deep neural network) model be used to predict MPG values on Auto MPG dataset using TensorFlow?
- How can a sequential model be built on Auto MPG dataset using TensorFlow?
- How can a sequential model be built on Auto MPG using TensorFlow?
- How can predictions be made on Auto MPG dataset using TensorFlow?
- How can model be evaluated based on Auto MPG using TensorFlow?
- How can model be fit to data with Auto MPG dataset using TensorFlow?
- How can predictions be made about the fuel efficiency with Auto MPG dataset using TensorFlow?
- How can data be normalized to predict the fuel efficiency with Auto MPG dataset using TensorFlow?
- How can data be cleaned to predict the fuel efficiency with Auto MPG dataset using TensorFlow?
- How can data be imported to predict the fuel efficiency with Auto MPG dataset (basic regression) using TensorFlow?
- How can data be split and inspected to predict the fuel efficiency with Auto MPG dataset using TensorFlow?
- How can a Convolutional Neural Network be used to build learning model?
- How can Tensorflow be used to export the model built using Python?
- How can Tensorflow be used to export the built model using Python?
- How can Tensorflow be used to define a model for MNIST dataset?

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

Tensorflow is a machine learning framework that is provided by Google. It is an open−source framework used in conjunction with Python to implement algorithms, deep learning applications and much more. It is used in research and for production purposes.

Tensor is a data structure used in TensorFlow. It helps connect edges in a flow diagram. This flow diagram is known as the ‘Data flow graph’. Tensors are nothing but multidimensional array or a list.

The dataset we use is called the ‘Auto MPG’ dataset. It contains fuel efficiency of 1970s and 1980s automobiles. It includes attributes like weight, horsepower, displacement, and so on. With this, we need to predict the fuel efficiency of specific vehicles.

We are using the Google Colaboratory to run the below code. Google Colab or Colaboratory helps run Python code over the browser and requires zero configuration and free access to GPUs (Graphical Processing Units). Colaboratory has been built on top of Jupyter Notebook. Following is the code snippet −

print("DNN model") history = dnn_horsepower_model.fit( train_features['Horsepower'], train_labels, validation_split=0.2, verbose=0, epochs=100) print("Error with respect to every epoch") plot_loss(history) x = tf.linspace(0.0, 250, 251) y = dnn_horsepower_model.predict(x) plot_horsepower(x, y) test_results['dnn_horsepower_model'] = dnn_horsepower_model.evaluate( test_features['Horsepower'], test_labels, verbose=0)

Code credit − https://www.tensorflow.org/tutorials/keras/regression

DNN refers to a deep neural network, and in this case it has a single input, i.e the ‘Horsepower’.

This model is fit to the training data.

The statistical parameters stored in ‘history’ is plotted on the console.

The predictions are made and these are evaluated using the ‘evaluate’ method.

Advertisements