Once you have created your model, you need to compile it before you can train it. The compile() method takes three arguments:
- Loss function: This is a function that measures the error between the model's predictions and the ground truth labels.
- Optimizer: This is an algorithm that updates the model's parameters to reduce the loss function.
- Metrics: These are measures of the model's performance on the training and test data.
The following code shows how to compile a model using the categorical crossentropy loss function, the Adam optimizer, and the accuracy metric:
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
Once the model has been compiled, you can train it using the fit() method.
Example
The following code shows an example of how to create and compile a model:
from keras.models import Sequential
from keras.layers import Dense
# Create the model
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(784,)))
model.add(Dense(10, activation='softmax'))
# Compile the model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# Train the model
model.fit(x_train, y_train, epochs=10)
This code will create a model with two dense layers, each with 128 neurons. The first layer will use a ReLU activation function, and the second layer will use a softmax activation function. The model will be compiled using the categorical crossentropy loss function, the Adam optimizer, and the accuracy metric. The model will then be trained on the training data for 10 epochs.
