How can Tensorflow be used with Estimators to evaluate the model using Python?

Tensorflow can be used with the estimator to evaluate the model with the help of the ‘evaluate’ method that is present in ‘classifier’ module.

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.

The model is trained using iris data set.


eval_result = classifier.evaluate(input_fn=lambda: input_fn(test, test_y, training=False))
print('\nTest dataset accuracy is: {accuracy:0.3f}\n'.format(**eval_result))

Code credit −


INFO:tensorflow:Calling model_fn.
WARNING:tensorflow:Layer dnn is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2. The layer has dtype float32 because its dtype defaults to floatx.
If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2.
To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2020-09-10T01:40:47Z
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.
INFO:tensorflow:Inference Time : 0.21153s
INFO:tensorflow:Finished evaluation at 2020-09-10-01:40:47
INFO:tensorflow:Saving dict for global step 5000: accuracy = 0.96666664, average_loss = 0.42594802, global_step = 5000, loss = 0.42594802
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 5000: /tmp/tmpbhg2uvbr/model.ckpt-5000
Test dataset accuracy is: 0.967


  • Once the moel is trained, some information on the performance can be obtained.

  • No parameter is passed to the ‘evaluate’ function.

  • The input_fn for eval only yields a single epoch of data.

  • The eval_result dictionary contains the average_loss (mean loss per sample), the loss (mean loss per mini-batch) and the value of the estimator's global_step (the number of training iterations it underwent).