The last method we will implement for our SimpleCNN is the fit method. This function triggers training for our CNN. Our fit method takes four input:
| Argument | Description |
| X_train | Training data |
| y_train | Training labels |
| X_test | Test data |
| y_test | Test labels |
The first step of fit is to initialize tf.Graph and tf.Session. Both of these objects are essential to any TensorFlow program. tf.Graph represents the graph in which all the operations for our CNN are defined. You can think of it as a sandbox where we define all the layers and functions. tf.Session is the class that actually executes the operations defined in tf.Graph:
def fit(self, X_train, y_train, X_valid, y_valid): """ Trains a CNN on given data Args: numpy.ndarrays ...
