{"id":78460,"date":"2020-06-10T15:36:05","date_gmt":"2020-06-10T10:06:05","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=78460"},"modified":"2021-08-25T13:54:53","modified_gmt":"2021-08-25T08:24:53","slug":"compile-evaluate-predict-model-in-keras","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/compile-evaluate-predict-model-in-keras\/","title":{"rendered":"Compile, Evaluate and Predict Model in Keras"},"content":{"rendered":"

Welcome to DataFlair Keras Tutorial series.<\/strong> This chapter explains how to compile, evaluate and make predictions from Model in Keras<\/strong>.<\/p>\n

\"Model<\/a><\/p>\n

Keras Compile Models<\/h2>\n

After defining our model and stacking the layers, we have to configure our model. We do this configuration process in the compilation phase.
\nBefore training the model we need to compile it and define the loss function, optimizers, and metrics for prediction.<\/p>\n

We compile the model using .compile()<\/strong> method.<\/p>\n

model.compile ( optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors)<\/pre>\n
Optimizer, loss, and metrics are the necessary arguments.<\/p>\n
Keras provides various loss functions, optimizers, and metrics for the compilation phase.<\/p>\n
Loss Function in Keras<\/h3>\n
These are available in the losses module and is one of the two arguments required for compiling a Keras model.<\/p>\n
from keras import losses<\/pre>\n
Below are the various available loss functions.<\/p>\n