Intelligent Mobile Projects with TensorFlow

Predicting with the drawing classification model

Take a look at the train_model.py file in the models/tutorial/rnn/quickdraw folder. When it starts to run, an Estimator instance gets created in the create_estimator_and_specs function:

  estimator = tf.estimator.Estimator(      model_fn=model_fn,      config=run_config,      params=model_params)

The key parameter passed to the Estimator class is a model function called model_fn that defines:

• Functions to get the input tensor and create convolutional, RNN, and final layers
• Code to call those functions to build the model
• The loss, optimizer, and prediction

Before returning a tf.estimator.EstimatorSpec instance, the model_fn function also has a parameter called mode which can have one of the following three ...