How can Tensorflow be used with Estimator to predict the output using Python?

TensorflowPythonServer Side ProgrammingProgramming

The ‘predict’ method is called on never before seen data and the predictions and the actual value is displayed on console.

Read More: What is TensorFlow and how Keras work with TensorFlow to create Neural Networks?

We will use the Keras Sequential API, which is helpful in building a sequential model that is used to work with a plain stack of layers, where every layer has exactly one input tensor and one output tensor.

A neural network that contains at least one layer is known as a convolutional layer. We can use the Convolutional Neural Network to build learning model. 

TensorFlow Text contains collection of text related classes and ops that can be used with TensorFlow 2.0. The TensorFlow Text can be used to preprocess sequence modelling.

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.

An Estimator is TensorFlow's high-level representation of a complete model. It is designed for easy scaling and asynchronous training.

Example

for pred_dict, expec in zip(predictions, expected):
   class_id = pred_dict['class_ids'][0]
   probability = pred_dict['probabilities'][class_id]
   print('Prediction is "{}" ({:.1f}%), expected "{}"'.format(
      SPECIES[class_id], 100 * probability, expec)
   )

Code credit −https://www.tensorflow.org/tutorials/estimator/premade#first_things_first

Output

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from /tmp/tmpbhg2uvbr/model.ckpt-5000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
Prediction is "Setosa" (91.3%), expected "Setosa"
Prediction is "Versicolor" (52.0%), expected "Versicolor"
Prediction is "Virginica" (63.5%), expected "Virginica"

Explanation

  • Once the ‘predict’ method is called, the predictions are made.

  • These values are displayed on the console, along with their confidence level.

raja
Published on 12-Feb-2021 11:50:34
Advertisements